Papers

Contrastive Language-Image Pre-training models are widely reused across downstream interfaces, including feature extraction, retrieval, reranking, and selection. Existing CLIP backdoor, however, usually validate attacks on a small attack-native task, leaving unclear whether the same poisoned checkpoint remains exposed, weakens, or becomes not applicable when reused through other interfaces. We introduce DIFE, a Deployment-Interface Footprint Evaluation framework that audits backdoored CLIP checkpoints across deployment interfaces. DIFE makes various evaluations comparable by specifying each interface's component readout, trigger channel, target event, reference condition, and metric. DIFE also introduces effective-footprint diagnosis to identify the reusable CLIP component or component combination that carries exposure and explains where risk transfers. Auditing reproduced CLIP backdoors with DIFE reveals a structured landscape: native success is not a checkpoint-level risk certificate, exposure follows component footprints, text-side poisoning does not yield textual-encoder control, and some coupled attacks remain mechanism-bound. This audit reveals a import gapin existing CLIP backdoors: a textual encoder that itself becomes a reusable carrier of adversarial behavior. We therefore introduce BadTextTower to fill this gap. BadTextTower produces strong text-conditioned retrieval, reranking, and selection exposure while leaving visual-only reuse nearly clean.

Tool-using LLM agents are shifting the unit of computation from explicit human-issued commands to model-driven tasks with stateful consequences. Yet today's agent runtimes still expose tools as isolated RPCs. This interface gives runtimes a convenient integration point, but it lacks a task-scoped execution boundary for commit, rollback, recovery, and audit across multi-step agent workflows. We argue that this mismatch calls for a runtime containment boundary rather than another per-call guardrail. This paper introduces Cordon, a transactional runtime system for staging and validating irreversible agent effects before commit. A semantic transaction is a task-level execution boundary that binds tool intents and runtime-tracked result lineage to reversible local state, staged external effects, delegated authority, and audit metadata. Cordon implements this abstraction with a transaction manager that tracks derived result objects, executes reversible mutations in shadow state, stages outward-facing actions in an effect outbox, and records recovery metadata. The runtime then validates the composed execution flow before it commits state or releases external effects. Our evaluation across adversarial and benign workflows shows that Cordon exposes cross-step violations missed by existing defenses. It also reduces irreversible-effect failures while preserving benign task completion with modest approval and latency overhead.

LiDAR sensors are widely deployed in autonomous systems for safety-critical 3D perception. We identify a previously unexplored attack surface in which dormant malware, embedded in the LiDAR sensing pipeline, remains inactive during normal operation and is triggered externally after deployment, without access to sensor hardware or networking at attack time. This malware was developed in a closed research test environment with vendor technical support, rather than by exploiting an inherent production supply-chain vulnerability. To trigger the malware, we repurpose the sensor's own native dual-return signal processing as a covert channel for a modulated optical signal delivered into the environment. Once triggered, the malware performs false data injection and suppression on static and mobile platforms. Unlike optical spoofing, where the transmitted signal is itself the attack, here it carries only a small key that the sensor decodes with existing signal processing. We establish feasibility with static triggering at 300~ft and drive-by runs reaching 35 mph, and verify that injected artifacts are taken up as detections by a fine-tuned 3D object detector. On a deployed tactical autonomous vehicle running an unmodified production autonomy stack, we demonstrate both fail-safe and fail-dangerous impact: emergency stop, mission abort, and collision. These results motivate stronger integrity guarantees across LiDAR development and deployment pipelines.

Banks face two threat families with fundamentally different detection requirements: signature-based fraud (card-not-present attacks, account takeover, ATM cloning) and behavioural financial crime (structuring, layering, mule networks, business email compromise). Static rule engines catch high-velocity events but remain blind to BEC payment redirection, session hijacking, and laundering layering, which are engineered to resemble legitimate activity at the individual level. This paper presents an autonomous AI security agent acting independently at low- and medium-risk tiers and escalating to a human analyst or compliance officer for high-risk and critical actions for retail and corporate banking using a three-component fusion architecture across two parallel event streams: transactions (card fraud, ACH/wire fraud, AML) and sessions (account takeover, hijacking, SIM-swap, insider abuse). Each stream combines an LSTM sequence model of per-account behaviour, a statistical velocity/threshold monitor, and a graph module capturing account-counterparty patterns (fan-in, fan-out, pass-through ratio) for laundering detection. Experiments on a synthetic log of 237,669 transactions and 113,508 sessions across 13 threat categories and 3,470 accounts show that the agent achieves an overall F1 of 0.787 (transaction) and 0.867 (session), versus 0.562/0.733 for a rule-based baseline and 0.655/0.713 for an LSTM-only baseline. The agent also incorporates a customer-facing verification chatbot (96.6% identity accuracy, 86.8% mass-reset detection) and an analyst case-summary assistant (99.3% action recommendation F1), with critical-tier response latency under 0.43 ms at the 95th percentile.

Snowpark enables data engineering and AI/ML workloads in Snowflake by executing user-defined functions in secure sandboxes. Many of these workloads require external connectivity to access cloud APIs, external databases, or feature stores, creating a dependability challenge: how to provide transparent network access while preserving strict multi-tenant isolation and resource fairness. This paper presents Secure Network Access in Snowpark (SNAS), a production architecture for secure external communication from sandboxed workloads. SNAS combines Extended Berkeley Packet Filter (eBPF) packet filtering, Generic Network Virtualization Encapsulation (GENEVE) overlay networks, and distributed egress proxies for policy-driven egress control with low overhead. We describe the design, deployment, and measured production behavior of SNAS, including an eBPF-based bandwidth limiter using the Earliest Departure Time (EDT) algorithm, dual-tier policy enforcement, and safeguards for connection limiting and port exhaustion. SNAS is deployed across all Snowflake regions and supports large-scale production workloads including petabyte-scale data transfer and latency-sensitive external integrations.

Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and interleave legitimate authority language with factual content. We demonstrate this gap with a benchmark of 122 tasks across five professional domains (financial, legal, medical, scientific, DevOps) built on real retrieved documents – actual SEC filings, Federal Register rules, PubMed abstracts, arXiv papers, and GitHub postmortems – paired with LLM-generated tasks and camouflaged payloads that were not human-validated. Paraphrasing, the strongest defense on synthetic benchmarks, shows no statistically significant attack success rate reduction on real documents (p=0.500) while degrading utility from 91.8% to 82.8%. We introduce PARSE (Provenance-Aware Retrieval Sanitization), a domain-aware, fact-preserving sanitization pipeline that classifies each sentence by injection likelihood, extracts structured facts before rewriting, and verifies fact preservation via a consistency-checking loop. A directiveness gate routes 59% of real enterprise documents to a lightweight path, concentrating computational cost on high-risk documents. PARSE achieves 15.6% attack success rate – a 39% reduction versus the 25.4% baseline – at 86.9% utility, the largest reduction of any condition evaluated (h=-0.245), nominally significant (p=0.014) but not surviving correction for multiple comparisons. Practitioners should evaluate defenses on domain-matched real documents, not synthetic proxies.

Cloud-hosted transformer and large language model (LLM) inference creates a direct confidentiality problem: user prompts may contain sensitive code, business data, personal information, or regulated documents, yet remote serving exposes intermediate state to the cloud software stack and accelerator runtime. Fully homomorphic encryption (FHE) keeps accelerator-side execution ciphertext-only, but end-to-end LLM inference remains expensive because linear layers are interleaved with non-linear, cache-state, and refresh-sensitive operators. CPU trusted execution environments (TEEs) can execute those operators natively, but a CPU TEE alone does not define how an untrusted accelerator should participate. We present Bifrost, a hybrid TEE-FHE serving architecture in which secrets are provisioned only to an attested CPU TEE, while the accelerator, device memory, driver/runtime stack, and host software remain outside the trusted computing base. Bifrost uses FHE as a secure delegation mechanism for projection and feed-forward linear layers on accelerator-backed CKKS, while non-linear operators, attention-side control logic, KV-state transitions, and decrypt-then-encrypt refresh execute inside the CPU TEE. Bifrost+ further applies a prefill/decode split: prompt-side KV state is built inside the CPU TEE, and only decode-side state enters the hybrid ciphertext path. In an estimator-style comparison matching Euston's methodology, Bifrost reduces projected latency by 9.25x on GPT-2 (1.5B) and 9.91x on LLaMA 3 (8B). In direct CKKS/FHE deployments, Bifrost+ reduces TTFT by 14.6-45.8x on GPT-2 (124M) and 15.3-53.4x on Qwen3 (0.6B). The systems lesson is selective encrypted execution: use FHE only where ciphertext-only accelerator delegation is required, and keep non-linear, refresh, and prompt-side work inside the CPU TEE.

Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to the lossy transformation of semantic information during compilation. Recent advances in machine learning, large language models (LLMs), and agentic AI systems have accelerated the adoption of AI-augmented binary reversing. Yet, the resulting body of work has become increasingly fragmented across reversing domains, artifact representations, learning approaches, and evaluation practices. This paper presents the first comprehensive systematization of knowledge on AI-augmented binary reversing. We collect 246 research papers published since 2015, and organize them into 22 binary reversing domains according to the inference tasks. We further introduce a unified taxonomy spanning conventional and AI-augmented reversing pipelines. Our taxonomy connects traditional analysis techniques, binary-derived artifacts, representation strategies, learning paradigms, and downstream inference tasks, while clarifying the emerging roles of LLMs and agentic AI systems. By establishing a common vocabulary and structured framework, we offer a holistic view of the field's evolution over the past decade. Our study reveals common structures underlying seemingly disparate approaches, highlights persistent technical challenges and evaluation gaps, and identifies promising opportunities for future research. Collectively, these insights clarify the current state of the field and provide a foundation for the next generation of evidence-grounded and practically deployable AI-augmented binary reversing systems.

The CPU-side large language model (LLM) tokenizer is a critical security gap in LLM serving through a confidential computing stack with CPU and GPU trusted execution environments (TEEs). Tokenizers converts the prompts through table-driven lookups, and the resulting memory access patterns are a powerful source of side-channel leakage. Recent work demonstrates end-to-end recovery of user prompts from tokenizer access pattern on production Intel TDX. However, a drop-in use of the popular tree-based Oblivious RAMs (e.g., PathORAM) to prevent access-pattern leakage introduces $\sim$13$\times$ tokenizer slowdown, resulting in 10-58% higher time-to-first-token (TTFT). In this paper, we present OTRO, an efficient, oblivious tokenization path tailored to latency-critical LLM serving. OTRO relies on square-root ORAM for fast single-access lookups, but avoids its prohibitive $O(N\log^2N$) rebuild cost every $\sqrt{N}$ accesses through three key innovations. First, OTRO provides a pool of replicated square-root ORAM instances that utilize the read-only nature of tokenizer table. Second, an epoch-based rotation policy decouples accesses from rebuilds and pads each epoch with dummy accesses to its boundaries, minimizing observable information. Lastly, chunked KV-cache-aware tokenization further overlaps rebuilds with GPU prefill and minimizes the instance count. Implemented as modules in HuggingFace Tokenizers and nano-vLLM, running within a TDX-enabled CVM with an NVIDIA H100 GPU, OTRO limits TTFT overhead to at most 4.5%, keeps tokenizer-induced latency under 10% of total TTFT, and adds less than 0.5 GB of memory overhead while reducing the tokenizer's observable leakage across various model families and sizes.

Achieving reproducibility, quantity, and diversity in vulnerability datasets has long been viewed as an inherent three-way trade-off, where improving one dimension often comes at the cost of the others. In practice, reproducibility has been the dimension most often neglected. This has limited what can be automatically extracted from historical bug datasets, and has reduced their utility for downstream security research. In this work, we propose a method to produce a new security dataset which ensures reproducibility for diverse vulnerabilities at scale by identifying the key obstacles to large-scale bug reproduction and addressing them with general solutions. Using this method, we introduce full reproducibility to the largest open source software vulnerability dataset (OSS-Fuzz) and construct the ARVO dataset (an Atlas of Reproducible Vulnerabilities in Open-source software). ARVO is a large-scale dataset consisting of over 6,100 real-world vulnerabilities across 311 projects. Focusing on reproducibility, ARVO differs from existing datasets by providing each vulnerability in a form that can be consistently rebuilt, triggered, and analyzed across versions. Reproducibility also enables automatic identification of the corresponding patch for each vulnerability and supports direct interaction with vulnerabilities after code changes, capabilities that existing large-scale datasets do not provide. In our evaluation, ARVO successfully reproduces 81% of vulnerabilities and achieves 89.4% accuracy on the located patches. We also discuss ARVO's influence on both upstream practices and downstream security research.

We start from a small open question, where Hetzl and Vierling asked whether two theories of induction, open induction and clause set cycles, are incomparable. They proved one direction and left the other open. Here we close it, and the proof is almost embarrassingly short, because the rules for addition can only fire when the first argument is $0$ or a successor, a Skolem constant is neither, so the terms $a{+}b$ and $b{+}a$ can never be touched, and a machine that can never touch them can never prove they are equal. The thing that separates the two theories is the order of two constants, and that order is a fact about numbers, not about symbols. We extract from this proof a small general principle, the Syntactic Invariance Principle, that names the shape of such arguments. We then close with a few speculative remarks on how this same shape appears, informally, in the known barriers to settling $\mathsf{P}$ versus $\mathsf{NP}$, where each barrier seems to point to a level of description that the techniques in the barrier cannot reach. We raise this as a suggestion rather than a theorem, since the analogy is real but we do not push it past the point where we can defend it. Along the way we raise an open question that the analogy suggests but does not settle, on whether a fast algorithm for $\SAT$, were it to exist, would always be exhibitable as a machine you can write down or whether it could be found, in some cases, only as a function on the numbers.

Internet blackouts, occurring due to technological mishaps or intentional governmental action, prevent citizens from accessing the internet. Citizens in regions where internet blackouts are common have utilized blackout-resistant technologies to maintain communication. Such technologies often rely on mobile mesh networks to provide limited messaging services. However, no technology currently exists which can provide continued access to knowledge sources on the web during a blackout. We present Cache to the Future (CttF): a system to cache and deliver static content hosted on the web during a blackout. CttF's distributed community ratings crowdsources caching at scale while cryptographic constructs (digital signatures, proofs-of-work) mitigate adversarial interference. Our realistic simulations demonstrate CttF delivering content at city-scale across a wide range of benign and adversarial scenarios.

Neuro-symbolic AI (NeSy) pairs neural perception with symbolic reasoning, making it attractive for high-stakes domains where explainability and structured inference are required. However, this hybrid architecture introduces an enlarged attack surface spanning five layers: neural perception, symbolic knowledge bases, reasoning engines, agentic orchestration, and data stores – each exploitable in ways absent from purely neural systems. This paper makes six contributions: (1) formal definitions of NeSy Attack Surface, Symbolic Integrity Violation (SIV), and Cross-Layer Amplification Ratio $\mathcal{X}$, decomposed into neural-caused and autonomous symbolic sensitivity components; (2) a unified threat model extending MITRE ATLAS with 11 NeSy-specific tactic extensions and a five-profile attacker taxonomy; (3) a symbolic-layer threat catalogue covering knowledge graph (KG) poisoning, ontology-merging, and inference-engine subversion; (4) analysis of cognitive risks – automation bias, authority bias, and sycophantic reinforcement – structurally amplified by NeSy's explicit logical explanations relative to black-box neural outputs; (5) interdisciplinary mitigations with measurable acceptance criteria aligned to NIST AI 600-1 and the EU AI Act; (6) three empirical benchmarks: (E1) targeted KG poisoning achieves break-even SIV at injection budget $B=5$ on a 205-entity medical KG, with a KG-specific stealth/SIV trade-off; (E2) PGD-10 at $\varepsilon=0.01$ yields $\mathcal{X}=5.884$ (95% CI $[4.64,\, 8.00]$, $p<0.0001$), confirmed adversarially specific by a matched-random baseline ($E^{R}_{\mathrm{rand}}=0$), on a DistilBERT+ProbLog pipeline; (E3) single-axiom OWL edits achieve 93.3% SIV success with 100% Pellet-consistency stealth, but held-out STIX detection fails at 50% (random-guessing level), an open problem.

In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains. Consequently, tracking and verifying historical contributions is essential for model provenance and intellectual property protection. However, existing watermarking methods are mainly designed for single-user, one-time embeddings, often fail under repeated model derivation and incremental updates. To address this problem, we propose LineageMark, a multi-user white-box watermarking framework for model derivation chains. The framework encodes watermarks in model parameters using a projection-based approach. Stable carriers are first selected to reduce sensitivity to model changes, each watermark bit is then represented as a projection statistic over these carriers. Additional watermark insertions introduce only bounded perturbations in the projection space, and margin constraints are used to maintain signal integrity. We evaluate the effectiveness of LineageMark in multi-stage model derivation chains. Experimental results show that LineageMark preserves contributor watermarks across multi-stage derivation and supports incremental multi-user watermark insertion. Furthermore, it exhibits robustness against perturbations such as re-watermarking, fine-tuning, quantization, and pruning.

The demand for privacy-compliant AI has amplified the need for machine unlearning; yet, existing retraining or distillation-based methods remain unverifiable and computationally costly. We introduce TrustErase, a verifiable, data-free unlearning framework leveraging passport-embedded representations for instant, modular, and auditable forgetting. By treating passports as cryptographic keys within parameter-efficient adaptation layers, TrustErase enables the removal of specific classes or datasets through simple deactivation, without retraining, fine-tuning, or access to the original data. A singular value based decomposition conceals passports within model weights, ensuring that unlearning actions remain transparent and provably compliant. Evaluations on MNIST, CIFAR10 and CIFAR100 show that TrustErase matches or exceeds state-of-the-art benchmarks such as DELETE, L2UL, and Boundary Shrink, while operating in a strictly data-free regime. Ultimately, TrustErase establishes a new paradigm for trustworthy, accountable, and instantly forgettable AI systems.

Physical cyber systems have brought about new threats and challenges in detection and immediate response. This study examines how Graph Neural Networks (GNNs) can be used to aid cybersecurity and drone management in a physical cyber system comprising of cyber intrusions and unmanned aerial vehicles (UAVs). By providing a bridge between structural understanding of graphical neural networks, this work has provided an integrated procedure that allows intrusion detection systems to educate on underlying network structures, identify malicious activity, and facilitates drone response measures. Based on an emulation-based case study, cyberattacks models were created to provoke the responses of the drones, which proved that graph-based learning can assist with the situational awareness, swarm coordination, and adaptive maneuver. According to the performance valuation, this method has a detection rate of 94.2, average area under the receiver operating characteristic (ROC) of 0.955 and an average response time of 1.4 seconds. Comparative experiments reveal that proposed GraphSAGE network is more effective than the Graphical Convolutional Networks (GCNs) and Graphical Attention Networks (GATs) in the identical situation. Such findings prove that graphical neural networks can be used to avert intrusion and response of dynamic cyber-physical systems.

Because of their ability to enable new forms of cryptanalysis, quantum computers pose a threat to the cryptographic algorithms that are widely used to secure contemporary computer systems. A practical quantum computer may emerge within the next ten years or so, but due to theorised "harvest now, decrypt later" style attacker behaviour, mitigations are necessary today. Recent advances in cryptography and security architecture show promise in supporting the design of systems that exhibit resilience against quantum-enabled cryptanalysis, however there is a key gap in the literature around the subject of deriving tolerances for such systems. In this paper, we introduce the concept of rotation time as a measure of crypto agility, and derive an approximation that links rotation time tolerance to security risk tolerance. Historical CVE data is used to calculate illustrative values for rotation time tolerance, which is found to be of the order of hours to days. This demonstrates that using crypto agility in conjunction with hybrid encryption is an effective approach for designing quantum-resilient systems, but may necessitate challenging technical and operational tolerances in order to meet organisational risk tolerances.

AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and disseminate sensitive information. Much of prior research on data leakage risks in agents has focused on adversarial data exfiltration through prompt injections and jailbreaks. However, sensitive information may also be exposed during non-adversarial use, creating leakage risks even when users issue benign requests. We report a joint evaluation by the Singapore AI Safety Institute and the Korea AI Safety Institute examining agent data leakage in 12 realistic, non-adversarial tasks spanning customer support, DevOps, web automation, and enterprise and personal productivity. The evaluation covers five risk types: lack of data awareness, audience awareness, policy compliance, data minimization, and access-boundary awareness. Both institutes tested a common set of scenarios mirroring real-world deployments using independent testing environments and task-specific LLM-judge rubrics. Across the three tested agents, none achieved fully correct and fully safe execution across all scenarios. Successful task completion often coincided with data-handling failures such as accessing unnecessary information or disclosing information to inappropriate recipients, indicating that capability and data-handling safety should be evaluated separately. Qualitative review also revealed claim-action mismatches, simulation-aware behavior, user-simulator role reversal, and interpretation gaps in automated judging. Overall, the results indicate that operational data leakage is a first-order agent-safety concern distinct from adversarial exfiltration and provide a methodology for future evaluations of agent data-handling safety.

Modern blockchain state management faces a critical scalability bottleneck: maintaining cryptographic commitments over hundreds of millions of entries becomes computationally prohibitive. Ethereum's transition to Verkle Trees: polynomial commitment accumulators reducing proof sizes from O(width * depth) to O(depth) via constant-size IPA vector commitments, is a critical step toward stateless operation. Yet, current implementations exhibit pathological characteristics that burden home validators. We identify four inefficiencies in the reference go-verkle implementation \cite{kaur2025goverkle, kaur2025goethereum}: (1) phantom node creation during non-existent account deletion; (2) 64-byte database keys triggering excessive LSM-tree compaction; (3) redundant memory copying in proof deserialization; (4) a Proof of Absence wire format incompatibility causing non-deterministic serialization. We present Fractional Verkle Trees (FVT), a hypertree decomposition partitioning global state into N independent sub-accumulators coordinated by a Merkle commitment tree, achieving improved cache locality, zero-lock-contention goroutine-parallel commitment computation, and faster root recomputation (91 $\mu$s vs $\sim$500 ms). We address each inefficiency via existence checks, 32-byte SHA256 node references, zero-copy reference-counted buffers, and HashMap-based lexicographic deduplication. Benchmarks on Apple M1 Pro show 57% heap allocation reduction (566,760 to 242,004 bytes per 10K proofs), parallel insertion at 2,433 ns/op, and network-wide elimination of 4.85 PB/year across 6,000 full nodes, advancing the Ethereum stateless roadmap.

Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets. Ensuring the privacy of such data against extraction attacks has become a central concern. In this paper, we ask whether an attacker who can poison a portion of the training data can facilitate the leakage of a separate target record they have no access to. We answer in the affirmative and show that such leakage can be induced by a poisoning mechanism that reshapes the model's local loss landscape around the target completion. Our key insight is that poisoning to create a sharp loss minimum at the target, surrounded by elevated loss on nearby alternatives, forces the model to memorize the target as the unique low-loss solution in its neighborhood. The attack requires no architectural changes, and generalizes across centralized and federated learning settings. We demonstrate that the attack amplifies privacy leakage across language (up to 100% successful extraction), and vision-language models (up 90% successful extraction). We show that the attack is thwarted when the model is trained to be differentially private. However, we introduce a new attack that directly probes the loss landscape bypassing even differential privacy defenses.

Given their effectiveness in modeling the relational structure among network traffic flows, graph neural networks (GNNs) have been widely adopted in network intrusion detection systems (NIDSs). However, most existing GNN-based NIDS approaches focus on the relational structure of traffic flows, and treat them as temporally independent, which limits their ability to cope with evolving attack behaviors. Moreover, their reliance on supervised or semi-supervised learning often restricts generalization to unseen attacks. To address these limitations, we propose a novel self-supervised GNN-based framework. To the best of our knowledge, the proposed model is among the first self-supervised GNN-based NIDS models to explicitly leverage real timestamps, which provides faithful temporal dependencies for representation learning. We first construct a series of temporal graphs from network traffic flows according to their timestamps, and then employ an E-GraphSAGE and LSTM based encoder to fully extract temporal information and spatial dependencies of network traffic, without introducing time-costly attention mechanisms. A multi-view graph contrastive learning (GCL) scheme is introduced, where temporal, spatial, and feature contrasts are jointly performed to capture temporal continuity, preserve structural consistency, and improve the generalization and robustness of the learned representations, respectively. In addition, a gradient-norm-based adaptive weighting strategy is designed to optimize the contrastive loss weights. Experimental results on four representative NIDS datasets with real timestamps demonstrate that our method significantly outperforms existing self-supervised approaches and achieves performance comparable to the supervised state-of-the-art GNN method, while maintaining high computational efficiency.

Prior research suggests that differential privacy (DP) can enhance the robustness of federated learning (FL) against backdoor attacks. In this paper, we challenge this assumption. Through an empirical analysis of two baseline attack strategies, we uncover a fundamental tension in DP-FL: while bypassing DP allows state-of-the-art defenses to detect and filter malicious updates, complying with DP inadvertently masks their distinguishing statistical characteristics. Consequently, existing defenses become ineffective as DP reduces the raw backdoor signal. Building on this masking effect, we propose RING, a novel attack that explicitly exploits DP to conceal malicious contributions while maximizing attack impact. By collaboratively crafting adversarial perturbations, compromised clients reconstruct a strong backdoor signal during aggregation without triggering anomaly detection. RING operates as a perturbation layer that is agnostic to the underlying backdoor technique, making it broadly applicable and composable with existing attacks – a property that significantly amplifies the threat it poses to DP-FL. Extensive evaluations across four image and text datasets under non-iid distributions show that RING achieves an average attack success rate of 90.3% against six state-of-the-art defenses under a moderate privacy budget, an improvement of up to 38.4% over baseline strategies. Finally, we evaluate potential countermeasures and find that mitigating this threat incurs significant utility trade-offs, exposing a fundamental security gap in the deployment of differentially private FL.

SIM cards have been the key building block of user authenticationand security in cellular networks. While they are meant to serve as privacy protecting elements in cellular communications, they can be the root cause of privacy loss. Current eSIMs come with a fixed device profile–comprising a secret key, a certificate, and a unique eUICC identifier–that permanently binds every subscriber profile provisioned on the device to that device profile. This binding enables an attacker with the vantage point of a cellular operator to correlate subscriber identities back to a single device, piecing together a complete pattern of life–online activities, movement patterns, and real-world identity–even when users rotate subscriber identities or employ traffic obfuscation techniques. To mitigate this concern, we introduce Di5Guise, a privacy-enhancing architecture that breaks this correlation at its root by decoupling the device identity from the subscriber identity. Central to Di5Guise is vSIM, a virtualized SIM card that enables dynamic device profile provisioning, allowing each subscriber profile to be associated with a distinct, unlinkable device profile. Di5Guise establishes trust with the operator by ensuring that vSIM is running on secure hardware in a trustworthy state. We prototype Di5Guise on a Field Programmable Gate Array (FPGA) board and integrate it with srsRAN to demonstrate full compatibility with existing 5G infrastructure. Using a complex user correlation model, we show that Di5Guise reduces user re-identification accuracy from 93% to 49% when combined with obfuscation.

Polymarket has emerged as a prominent prediction market platform and one of the fastest-growing applications in DeFi. To achieve low-latency trading, it adopts a hybrid architecture that matches orders off-chain but settles them on-chain for final execution. This design creates a consistency gap we call Ghost Fills: an order that is successfully matched off-chain may later fail during on-chain settlement. To understand the security implications of this gap, we investigate such failed settlements by building GhostHunter, which reconstructs them from on-chain traces and attributes them to concrete attack patterns. Across 2,037,304 reverted matchOrders() transactions, we find that attackers exploit the time gap between matching and settlement to invalidate already matched orders before they are finalized on-chain. We identify four attack vectors, Nonce Bump, Balance Drain, Allowance Revoke, and Proxy Trap, realized via 37 evolving variants. These vectors account for 994,196 of the reverts, enabling risk-free prediction, arbitrage-bot hunting, and liquidity reward manipulation. The cancelled orders spare their owners $103.7 M in net losses that settlement would have locked in, and the attacks cost the operator 2.17 M POL (about $162 K) in gas. During peak hours, up to 24.3% of transactions reverted, causing de facto DoS attacks. We also find that code derived from the flawed contract still appears in 167 independent contracts across 10 chains holding at least $23 M in user funds, extending the impact beyond Polymarket. We have disclosed our evidence to affected parties, and the issue has been partially mitigated.

Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that attacker-published pages are transformed into endorsed claims. We introduce SearchGEO, a controlled evaluation framework for measuring endorsement corruption in LLM-based web-search agents, combining a web-evidence manipulation pipeline, a five-mode attack taxonomy, and multiple output-level metrics. We evaluate 13 LLM backends on 308 cases each. Results show that vulnerability patterns vary across backends: overall attack success rate (ASR) ranges from 0.0% on Claude-Sonnet-4.6 to 31.4% on Gemini-3-Flash, the strongest attack mode differs by model family, and the same deployment scaffold could amplify or decrease ASR on different backends. An auxiliary agent-skill probe, where endorsement becomes an install command, exposes a sharp split among otherwise robust backends: Claude over-rejects while GPT over-trusts. These findings argue for treating recommendation reliability under adversarial search content as a first-class dimension of backend safety evaluation.

When a person's records appear in k independent data silos, each protected by (epsilon, delta)-differential privacy, standard composition yields a valid (k*epsilon, k*delta)-DP guarantee for the joint output. This worst-case bound, however, does not answer the concrete inference question: at what k can an adversary actually identify a target person? This paper develops the information-theoretic framework needed to answer that question. We introduce cross-silo person-level DP (XSP-DP), a Pufferfish-style privacy notion whose adjacency relation captures all records of a single person across all silos simultaneously, and verify that the standard basic composition bound carries over to this adjacency model. Within this framework we prove that de-anonymization undergoes a phase transition at k* = Theta(log n / epsilon^2) (population size n, per-silo RR parameter epsilon): a Fano lower bound shows any estimator fails for k << k*, while a matching maximum-likelihood upper bound shows the attack succeeds for k >> k*. An explicit XOR + randomized-response construction demonstrates information synergy: each silo's output is individually uninformative about the target, yet the joint mutual information is strictly positive. For non-coordinated binary randomized-response mechanisms, we prove that de-anonymization is inevitable once k exceeds the threshold, establishing that cross-silo coordination is necessary. These results provide a baseline threat model and Theta-level threshold for cross-silo inference attacks under local DP.

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their safety remains a critical concern due to their susceptibility to adversarial prompt-based attacks. In this paper, we present UNIATTACK, an adversarial testing framework designed from a defense-oriented perspective to systematically construct effective black-box attack prompts. Unlike prior approaches that rely on static templates or iterative model-specific tuning, UNIATTACK extracts minimal but high-impact attack features from diverse existing attacks, optimizes them via a specialized attacker LLM, and composes them into flexible templates through automated refinement process. This feature-centric construction enables one-shot attacks that generalize across multiple models and safety categories, providing a practical tool for assessing LLM robustness. Our evaluation results shows that compared to the baselines, UNIATTACK achieves an average attack success rate (ASR) improvement of 64.63%-248.82% on models deployed with multi-layered defense mechanisms and it only takes 0.03%-4.96% cost of the baselines. UNIATTACK artifact is available at https://anonymous.4open.science/r/UniAttack-Artifact-30F1.

Distributed systems handle adversarial nodes through redundancy, which imposes a significant performance overhead. In blockchain systems, Byzantine fault-tolerant state-machine replication (BFT-SMR) is the replicated service that totally orders client transactions before execution. While prior research has primarily focused on designing novel consensus algorithms with improved performance, recent studies have shown that further gains can be achieved through configuration optimization. More precisely, replicas can monitor network latency to dynamically assign the leader role and tune voting weights, thereby improving consensus performance. However, we identify three vulnerabilities in this process that Byzantine nodes can exploit. To address these weaknesses, we propose Beware, a reconfiguration framework that filters out falsified latency reports, computes robust weight distributions, and applies machine learning to converge towards Byzantine-resilient configurations. Our evaluation shows that Beware reduces consensus latency by up to 45% compared to existing solutions.

Web user tracking has always been a cat-and-mouse game between privacy-conscious users and trackers. Recently, this conflict has driven a shift from third-party tracking toward first-party tracking (FPT) and server-side tracking (SST). By relocating tracking logic to the browser's first-party context or the website's backend, these mechanisms obscure data flows and render traditional client-side detection tools increasingly ineffective. Despite the growing adoption of these techniques, our understanding of their deployment at scale remains limited, and generalized protection mechanisms are lacking. In this work, we conduct a large-scale measurement of top sites to assess this shift and the prevalence of FPT and SST. We develop a provider-independent methodology to detect these mechanisms and find that over 54% of analyzed sites now deploy FPT or SST-related techniques. By clustering scripts based on their similarity and constructing a network graph, we demonstrate that the ecosystem is densely connected and dominated by major vendors like Google. Finally, we demonstrate that current filter lists are largely ineffective against first-party tracking, and we propose new rules to address this gap. We show that these rules block 63% more requests than traditional filter lists.

The web browser remains one of the most exposed remote attack surfaces on end-user systems, and memory-corruption flaws continue to play a central role in real-world browser exploitation. Despite a decade of intensive browser testing and bug-disclosure efforts, the community still lacks an explicit, defense-oriented systematization of the browser's low-level attack surface. Prior SoKs have surveyed browser vulnerabilities and mitigation techniques. However, these perspectives remain fragmented, leaving open a central question: how is the low-level attack surface of modern web browsers structured, and which parts of this surface remain underexplored by existing security testing? We approach this primary question through three sub-questions. (RQ1) How is the browser's attack surface structured along input classes and components? (RQ2) Where do memory corruption vulnerabilities arise within this taxonomy? (RQ3) What do these attack-surface patterns imply for existing browser security testing? To answer RQ1, we derive an architecture-grounded Input x Component x Privilege taxonomy that abstracts the architectures of browsers into a unified view. To answer RQ2, we map 2,233 memory corruption reports disclosed between 2016 and 2025 onto this taxonomy. To answer RQ3, we overlay a decade of academic browser fuzzers, classified by the targeted input class, onto the bug-density map. Our systematization reveals that current testing concentrates on well-explored components while bug-dense, high-impact surfaces remain insufficiently tested. Moreover, we identify three fuzzer deployment gaps, which are orthogonal to the academic efforts. Our work offers a structured foundation for future browser security research.