Papers

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both executable behavior and context-setting documentation, its deployment risk cannot be measured by single-shot audits or prompt-level red teams alone: a realistic attacker can use audit and runtime feedback to repeatedly rewrite the skill. We frame this risk as adaptive leakage – whether a budgeted attacker can iteratively revise a skill until it passes audit and produces verified runtime harm – and present \ours{}, a grey-box self-evolving red-team framework for measuring it. Proteus searches a formalized five-axis skill-attack space. Each candidate is evaluated through a unified audit-sandbox-oracle pipeline that returns structured audit findings and runtime evidence to guide cross-round mutation. Beyond initial evasion, Proteus performs path expansion, which finds alternative implementations of successful attacks, and surface expansion, which transfers learned implementation patterns to new attack objectives beyond the original seed catalogue. Across eight phase-1 cells, Proteus reaches 40–90% Attack Success Rate at $5$ rounds (ASR@5) with positive learning-curve slopes on both evaluated auditors. Phase-2 path/surface expansion produces 438 jointly bypassing and lethal variants, with SkillVetter bypassed at $\geq 93\%$ in every cell and AI-Infra-Guard, the strongest public auditor we evaluate, still admitting up to 41.3% joint-success. These results show that current skill vetting substantially underestimates residual risk when evaluated against adaptive, feedback-driven attackers.

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing red-teaming resources fall short of this scenario: prompt-injection benchmarks ship pre-built adversarial pages that whitelisted agents cannot reach, and generic LLM scanners probe the model API rather than its retrieved content. We present IPI-proxy, an open-source toolkit for red-teaming web-browsing agents against indirect prompt injection (IPI). At its core is an intercepting proxy that rewrites real HTTP responses from whitelisted domains in flight, embedding payloads drawn from a unified library of 820 deduplicated attack strings extracted from six published benchmarks (BIPIA, InjecAgent, AgentDojo, Tensor Trust, WASP, and LLMail-Inject). A YAML-driven test harness independently parameterizes the payload set, the embedding technique (HTML comment, invisible CSS, or LLM-generated semantic prose), and the HTML insertion point (6 locations from \icode{head\_meta} to \icode{script\_comment}), enabling parameter-sweep evaluation without mock pages or sandboxed environments. A companion exfiltration tracker logs successful callbacks. This paper describes the threat model, situates IPI-proxy among contemporary IPI benchmarks and red-teaming tools, and details its architecture, design decisions, and configuration interface. By bridging static benchmarks and live deployment, IPI-proxy gives AI security teams a reproducible substrate for measuring and hardening web-browsing agents against indirect prompt injection on the same retrieval surface attackers exploit in production.

The x402 protocol revives the HTTP 402 Payment Required status code to enable web-native micropayments across APIs, content, and agents. It combines synchronous HTTP authorization with asynchronous blockchain settlement and introduces a cross-layer attack surface absent from conventional web and on-chain payments. In this paper, we formally analyze x402 and empirically show that it is vulnerable in both design and implementation. We present five concrete attacks that reveal weaknesses in authorization, binding, replay protection, and web-layer handling, showing that x402 is vulnerable across multiple stages of the payment workflow. We validate these attacks through a reproducible testbed on local chains, Base Sepolia, and live endpoints and further audit three open-source SDKs and endpoints. Our results show that all five attacks are practical and can cause either unpaid service or paid-but-denied outcomes. We also propose practical mitigations.

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the behavioral integrity verification (BIV) problem: a typed set comparison between declared and actual capabilities over a shared taxonomy that bridges code, instructions, and metadata. The BIV framework instantiates this comparison by pairing deterministic code analysis with LLM-assisted capability extraction. The resulting structured evidence supports three downstream analyses: deviation taxonomy, root-cause classification, and malicious-skill detection. On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap: 80.0% of skills deviate from declared behavior, with four novel compound-threat categories surfaced. Root-cause classification finds that deviations are mostly oversight, not malice: 81.1% trace to developer oversight and 18.9% to adversarial intent, with 5.0% of skills carrying predicted multi-stage attack chains. On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.946, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.

Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona-Conditioned Adversarial Prompting (PCAP), which conditions adversarial search on diverse attacker personas (e.g., doctors, students, malicious actors) and strategy sets to explore realistic attack scenarios. By running parallel persona-conditioned searches, PCAP discovers transferable jailbreaks across different contexts and generates rich defense datasets with automatic metadata tracking. On GPT-OSS 120B, PCAP increases attack success from 57% to 97% while producing 2-6$\times$ more diverse prompts covering varied real-world scenarios. Critically, fine-tuning lightweight adapters on PCAP-generated data significantly improves model robustness (recall: 0.36 $\rightarrow$ 0.99, F1: 0.53 $\rightarrow$ 0.96) with minimal false positives, demonstrating a practical closed-loop approach from vulnerability discovery to automated alignment.

Ring signatures offer highly desirable privacy features like anonymity and ad-hoc group formation with high autonomy, but partially lack linkability and accountability features required for strict use-cases like consent management in healthcare. Existing signature schemes fail to natively integrate scoped linkability with decentralized accountability defined here on-demand unconditional deanonymization of signers without reliance on a trusted party (opener) or a separate cryptographic commitment. We introduce Deanonymizable Scoped Linkable Ring Signatures (DSLRS) to address this gap. DSLRS builds on previous linkable and accountable signature schemes and their cryptographic primitives to construct a new signature scheme that natively implement both privacy and trust features. Scoped linkability in DSLRS is achieved using "scopes" (context identifiers) and dynamic key images, effectively providing ring-independent scoped linkability and unlinkability across different scopes. DSLRS relies on k-of-N decentralized deanonymization network nodes to extract the signer's public key (identity) from ElGamal components built in the signature, achieving ring-independent decentralized accountability. The full DSLRS algorithms, formal property definitions and proofs, signature evaluation and experimental results from an implementation, and a blockchain-based instantiation and application of our scheme in consent management for clinical trials are provided. DSLRS is proved under the ECDLP and DDH hardness assumptions in the Random Oracle Model (ROM).

Existing Digital Twin (DT) approaches often lack semantic reasoning capabilities for effective cybersecurity modelling in Cyber-Physical Systems (CPS). This paper presents HySecTwin, a knowledge-driven digital twin architecture that places automated reasoning at the core of real-time threat detection. HySecTwin incorporates semantic modelling to transform heterogeneous CPS telemetry, device attributes, and operational relationships into machine-interpretable representations, combined with an embedded reasoning engine operating over contextualized system states. Unlike opaque detection methods, the framework integrates deterministic rule-based inference with hybrid fuzzy reasoning to generate explicit, interpretable, and auditable security assessments from live device telemetry. This enables context-aware monitoring of complex CPS environments while preserving transparency and trust. Experimental evaluation using a representative CPS testbed and MITRE ATT&CK campaign-inspired attack scenarios demonstrates sub-millisecond twin synchronization latency and up to 21.5% faster threat detection compared with deterministic reasoning alone. The results show that semantic modelling, semantic enrichment, and hybrid reasoning improve explainability and resilience without extra system overhead. HySecTwin provides a lightweight, containerized, and extensible framework for secure-by-design digital twin deployments in mission-critical infrastructures

Recent work on LLM-driven autonomous penetration testing reports promising results, but existing systems often bundle architectural, prompting, and tool-integration choices together. This makes it difficult to determine what is gained over a simple agent and harness. We present Cochise, a 630 LOC Python reference implementation for autonomous penetration-testing experiments. Cochise connects to a Linux execution host over SSH and supports attacking controlled target environments reachable from that jump host. The prototype implements a Planner–Executor architecture in which long-term state is maintained by the planner, while a ReAct-style executor issues commands over SSH and self-corrects based on command outputs. The scenario prompt can be adapted to different target environments. We evaluate the harness against a live third-party testbed, Game of Active Directory (GOAD). Cochise is intended not as a state-of-the-art penetration-testing agent, but as a reusable experimental infrastructure for comparing models, agent architectures, and penetration-testing traces. Alongside the prototype, we release replay and analysis tools: (i) cochise-replay for offline visualization of captured runs, (ii) cochise-analyze-logs and cochise-analyze-graphs for cost, token, duration, and compromise analysis, and (iii) a corpus of JSON trajectory logs from GOAD runs, so that researchers can study agent behavior without provisioning the 48–64 GB RAM / 190 GB storage testbed themselves. Tool demo video available at https://youtu.be/2mQimB1ufyI.

Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time. In black-box settings, defenders cannot modify model weights and must instead intervene at inference time. This setting creates three practical challenges: harmful intent may be hidden by educational or role-play framing, deep safety analysis can introduce non-trivial latency, and long adversarial contexts can dilute the local cues that simpler filters rely on. These challenges can expose an apparent thinking–output gap, where the model appears cautious during reasoning but still produces an unsafe final answer. To address this problem, we propose Safety Context Injection (SCI), an inference-time framework that separates safety assessment from task generation and prepends a structured external risk report as injected safety context for the protected model. The framework is instantiated in two complementary variants: Static Model Filtering (SMF), a lightweight one-pass guard for fast deployment, and Dynamic Agents Filtering (DAF), an agentic-loop-based analyzer that iteratively gathers and synthesizes evidence for ambiguous or long-context attacks. Across AdvBench and GPTFuzz, spanning base and reasoning models under five jailbreak families, both variants reduce attack success rate and toxicity in the evaluated settings. SMF offers an efficient low-latency option, while DAF is more effective when harmful intent is semantically disguised or dispersed across long contexts.

With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose a fundamentally new approach for multibit watermarking: introducing binomial encoding to directly encode every bit of the payload at every token position. We complement our approach with a stateful encoder that during generation dynamically redirects encoding pressure toward underencoded bits. Our evaluation against 8 baselines on up to 64-bit payloads shows that our scheme achieves superior message accuracy and robustness, with the gap to baseline methods widening in more relevant settings (i.e., large payloads and low-distortion regimes). At the same time, we challenge prior works' evaluation metrics, highlighting their lack of practical insights, and introduce per-bit confidence scoring as a practically relevant metric for evaluating multibit LLM watermarks.

Here is a further shortened version (pure text, no extra formatting, academic style preserved, no content change): Abstract. With the rise of AI-generated content (AIGC), phishing actors now possess richer linguistic capabilities and evasion techniques. Most existing detectors over-rely on mutable textual features, achieving high accuracy on clean data but degrading severely under text-focused adversarial manipulation. This mirrors the lab-to-real performance gap. We investigate invariant signals in phishing emails: even when attackers modify surface text, functional intent constrains relations among typed entities. Threat-actor tradecraft is described via high-level TTPs, but rule-based systems like Sigma express invariants only through manually curated, field-specific patterns, limiting flexibility. We introduce PhishSigma++, an entity-relation-based malicious email detector for RFC822 messages that generalizes Sigma's design. It extracts 40 typed entity classes, computes 5 cross-type relations to build a typed email graph, and uses particle swarm optimization (PSO) to select a sparse discriminative mask, supporting classification and type-level evidence summary. On 29,142 messages, PhishSigma++ achieves 0.9675 F1 on clean data and outperforms text-centric baselines under non-adaptive Good Word padding at h̊o}=0.8. It maintains 0.9579 F1, while a token-based Bayesian filter collapses to 0.0243 and a DistilBERT phishing checkpoint falls to 0.7284. Compared with traditional Sigma rules, PhishSigma++ offers higher detection, broader relational invariance coverage, and data-driven feature selection. We also show that thresholded typed relation scores encode a useful fragment of Sigma-style field conditions, unifying hand-crafted rule logic and learned relation masks in a single-email framework.

This study investigates the potential for deanonymizing services within the Invisible Internet Project (I2P) network through passive traffic analysis and machine learning techniques. The primary objective is to identify distinctive patterns in I2P traffic despite the encryption of its payload. To achieve this, a controlled laboratory environment was established to generate synthetic I2P traffic, providing a training dataset for machine learning models. Furthermore, Fano's inequality is employed to perform a theoretical analysis of anonymous data transmission in mix networks such as I2P, thereby supporting a data-driven approach to uncover causal relationships. In computer experiments, advanced deep learning methods - particularly Convolutional Neural Networks - are applied within the laboratory I2P network, and their effectiveness is further evaluated using real-world traffic data. The results indicate that the proposed methodologies do not compromise the anonymity guarantees of the I2P network.

Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds imperceptible perturbations into data before release to reduce learnability. At the post-training stage, unlearning removes previously acquired information from models to prevent unauthorized disclosure or use. While both defenses aim to preserve the right to withhold knowledge, their vulnerabilities and shared foundations remain unclear. Specifically, both unlearnability and unlearning suffer from issues such as shallow dememorization, leading to falsely claimed data learnability reduction or forgetting in the presence of weight perturbations. Moreover, input perturbations may affect the effectiveness of downstream unlearning, while unlearning may inadvertently recover domain knowledge hidden by unlearnability. This interplay calls for deeper investigation. Finally, there is a lack of formal guarantees to provide theoretical insights into current defenses against shallow dememorization. In this Systematization of Knowledge, we present the first integrated analysis of model dememorization approaches leveraging unlearnability and unlearning. Our contributions are threefold: (i) a unified taxonomy of unlearnability and scalable unlearning methods; (ii) an empirical evaluation revealing the robustness, interplay, and shallow dememorization of leading methods; and (iii) the first theoretical guarantee on dememorization depth for models processed through certified unlearning. These results lay the foundation for unifying dememorization mechanisms across the ML lifecycle to achieve a deeper immemor state for sensitive knowledge.

Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard tool for this purpose, yet existing attacks assume a single-table setting and ignore the multi-relational structure of real sensitive data. A core challenge in assessing privacy risks from membership inference attacks in multi-table settings is how to leverage auxiliary information from relations associated with the target table, such as its parent tables. Particularly, we study a practical setting in which such auxiliary information is available only when training the attack model. At inference time, the attacker observes only the attribute values of the target record from the target table. We propose FERMI (FEature-mapping for Relational Membership Inference), which resolves this gap by enriching single-table features with relational membership signal. Across three tabular diffusion architectures and three real-world relational datasets, FERMI consistently improves attack performance over single-table baselines, with TPR@$0.1$FPR rising by up to 53% over the single-table baseline in the white-box setting and 22% in the black-box setting.

Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner–executor architectures, where planners convert prompts into subtasks, roles, dependencies, and routing paths. This flexibility enables adaptive coordination, but exposes an attack surface in workflow formation: prompts can shape agent organization without modifying MAS infrastructure. We study this risk through social influence probing workflows to identify high-impact subtasks and malicious-signal propagation. The analysis reveals two vulnerabilities: workflow position can amplify or suppress a malicious signal, and sycophantic framing makes downstream agents more likely to relay it. We translate these findings into FlowSteer, a prompt-only workflow steering attack that converts vulnerability priors into one crafted prompt. FlowSteer aligns a malicious signal with influential task components and guides replanning toward dependencies that preserve propagation. Experiments show that FlowSteer increases malicious success by up to 55% over naive prompting, transfers across MAS setups, and remains effective with black-box topology inference. As FlowSteer biases the planning signals that generate the workflow, MAS defenses that inspect only the generated workflow provide limited protection. As such, we introduce FlowGuard, an input-side defense that reduces malicious success by up to 34% while preserving prompt utility. Our results position workflow formation as a new safety frontier for multi-agent LLM systems, opening a planning-time security perspective on how agent coordination itself can be attacked and defended.

Recent advances in Large Language Models (LLMs) have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag (CTF) benchmarks. However, current CTF benchmarks reuse existing challenges, which exposes them to data contamination and potential cheating. Notably, we confirmed these issues in practice by integrating web search tools into an existing agent. To address these limitations, we present CTFusion, a streaming evaluation framework built on Live CTFs. To achieve this, CTFusion preserves per-agent independence under a single team account and reduces competition impact by forwarding only the first correct flag per challenge. Moreover, we implement CTFusion as a Model Context Protocol (MCP) server on the widely used CTFd platform, which offers broad applicability to diverse CTF events and agent types. Through experiments with three LLMs, two agents, and five Live CTFs, we demonstrate that existing CTF benchmarks can be unreliable in assessing LLM-based agents, while CTFusion can serve as a robust solution for evaluating cybersecurity agents. We release CTFusion as open source to foster future research in this area.

Decompilers are useful tools used in reverse engineering to understand compiled source code. Reconstructing source code from compiled binaries is a challenging task, because high-level syntax, identifiers, and custom data types are generally lost as the compiler translates human-readable code to low-level machine code. Deterministic decompilers are useful tools for binary analysis, but can struggle to infer idiomatic syntax and identifier names. Generative AI models are a natural fit for reconstructing high-level syntax, identifiers, and types, but they can still suffer by hallucinating improper programming constructs and semantics. Instead of attempting to improve neural decompilers with more data and more training, we argue that compiler feedback can be used to dramatically improve the semantic correctness of neural decompiler outputs via search. Our system, Decaf (DECompilation with Automated Feedback), raises the neural decompilation rate from 26.0% on ExeBench to 83.9% on the Real -O2 split without sacrificing similarity to the original source code. We also find our automatic feedback methodology is highly effective for improving weaker neural decompilation models.

Enterprise AI is shifting from copilots to autonomous agents capable of executing workflows, negotiating outcomes, and making decisions with limited human oversight. As these systems extend across organizational boundaries, identity alone is insufficient: an agent's authority must also be explicit, constrained, auditable, revocable, and consistently interpretable by independent receivers. This paper analyzes representative enterprise use cases in insurance claims processing and supply chain integrity to surface structural gaps in existing identity and access models. It proposes a portable authorization model for autonomous agents based on issuer-authored authorization payloads, typed constraint algebra, decision-consistent evaluation semantics, delegation attenuation, governed semantic resolution, fail-closed processing, and pre-flight discovery. The model separates credential containers, authorization payload semantics, and enforcement engines, allowing profiles such as JWT/JWS, Verifiable Credentials, OAuth Rich Authorization Requests, or policy-engine bindings to preserve a common authorization meaning across trust boundaries.

A secure two-party computation protocol for running dynamic controllers over secret sharing has recently been proposed. Unlike encrypted control schemes based on homomorphic encryption, this protocol enables operating dynamic controllers for an infinite time horizon without controller-state decryption, controller-state reset, or input re-encryption. However, the two-party setting introduces additional online communication between the computing parties, which may hinder real-time feasibility. In this study, we demonstrate the feasibility of the protocol through implementation on a commercial cloud platform with an inverted pendulum testbed. Experimental results show that the proposed protocol successfully stabilized the pendulum despite the online communication overhead.

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of the agent acting as a disruptive "hub" within the user-agent-service chain remains largely overlooked. In this work, we expose a novel threat paradigm by introducing Mobius Injection, a sophisticated attack that weaponizes autonomous agents into zombie nodes to launch what we define as Agent-based and -Oriented DDoS (AbO-DDoS) attacks. Mobius Injection composes known indirect prompt injection and persistent agent components through a distinct structural mechanism named Semantic Closure, which induces sustained recursive execution of agent components through a single injection event. We demonstrate that this attack is lightweight for the adversary, can evade traditional volumetric DDoS monitors and input filters calibrated for low false-positive rates, and is highly configurable, allowing for surgical targeting of specific environments or model providers. To evaluate the real-world impact, we conduct extensive experiments across three representative claw-style agents and three mainstream coding agents, integrated with 12 frontier proprietary or open-weight LLMs. Our results demonstrate that Mobius Injection achieves substantial attack success across diverse tasks, driving single-node call amplification up to 51.0x. Under coordinated multi-node pressure, each infected node still drains about 123k–127k tokens on a shared five-GPU backend; benign request latency rises by abou 23x–24x, and coordinated infections eventually saturate shared capacity until benign traffic is effectively denied service.

Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability expansion, it also introduces a semantic supply-chain risk in which natural-language metadata and instructions can affect which skills are admitted, surfaced, selected, and loaded. We study SKILL.md - only attacks across three registry-facing stages of the Agent Skill lifecycle, using real ClawHub skills and realistic registry mechanisms. In Discovery, short textual triggers can manipulate embedding-based retrieval and improve adversarial skill visibility, achieving up to 86% pairwise win rate and 80% Top-10 placement. In Selection, description-only framing biases agents toward functionally equivalent adversarial variants, which are selected in 77.6% of paired trials on average. In Governance, semantic evasion strategies cause malicious skills to avoid a blocking verdict in 36.5%-100% of cases. Overall, our results show that SKILL.md is not passive documentation but operational text that shapes which third-party capabilities agents find, trust, and use.

Deep learning-based website fingerprinting has emerged as an effective technique for inferring the websites users visit. Although existing methods achieve strong performance on closed-world datasets, they often fail to generalize to real-world environments, especially under geographic and temporal shifts. This limitation fundamentally stems from the coupled effects of two key challenges: application-layer resource composition variability and observable feature instability induced by cross-layer encapsulation. Intertwined, these factors induce systematic shifts between underlying application semantics and observable traffic features. To address the above challenges, we propose SATA , a semantics-aware traffic augmentation framework. Specifically, SATA first performs application-layer semantic augmentation based on protocol rules, expanding the resource composition patterns within each flow and frame sequence patterns under protocol constraints. Based on these augmented frame sequences, we further introduce a cross-layer feature alignment mechanism via knowledge distillation. It aligns frame sequence with packet-length sequence features, enabling cross-layer feature alignment between enhanced semantics and observable sequences. Extensive experiments show that SATA successfully generates traffic patterns that are absent from the training set but genuinely exist in the test set, and significantly improves the performance of mainstream models across diverse and complex scenarios. In particular, in open-world settings, SATA improves ACC by 90.81% and AUROC by 48.37%. The source code of the prototype system is available at https://anonymous.4open.science/r/SATA-B6C2/.

As Model Context Protocol adoption grows, securing tool invocations via meaningful user consent has become a critical challenge, as existing methods, broad always allow toggles or opaque LLM-based decisions, fail to account for dangerous call arguments and often lead to consent fatigue. In this work, we present Conleash, a client-side middleware that enforces boundary-scoped authorization by utilizing a risk lattice to auto-permit safe calls within known boundaries while escalating risks, a policy engine for user-defined invariants, and a refinement loop that converts user decisions into reusable rules. Evaluated on 984 real-world traces, Conleash achieved 98.2% accuracy, caught 99.4% of escalations, and added only 8.2 ms of overhead for policy verification; furthermore, in a user study where N=16, participants significantly preferred Conleash scoped permissions over traditional methods, citing higher trust and reduced prompting.

Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieved documents introduce a new threat surface that can be exploited to launch split-knowledge attacks. In this attack, the adversary injects documents that are individually benign but create false associations when combined and fed to language models. This paper shows that the new attack is structurally invisible to existing per-document filters, like LlamaGuard. To address this issue in RAG, this work introduces TopoGuard, a family of graph theory-based methods specifically targeting the split-knowledge attacks by building a semantic similarity graph from retrieved documents and detecting contexts with malicious topology. Grounded on the theoretical analysis, the TopoGuard family has been proven to be effective and robust even with noisy inputs. Extensive experiments are conducted on two retrieval datasets and compared with multiple baseline methods. Specifically, the TopoGuard-$\lambda_2$+Entity catches 21$\times$ more attacks than LlamaGuard-2-8B at 1% FPR (32.6% vs 1.5% recall) on the HotpotQA dataset. Compared with production RAG detection systems using large language models, the proposed TopoGuard variants run efficiently at sub-millisecond latency and stay robust under adaptive adversaries and benign cross-domain queries.

Unmanned Traffic Management (UTM) federated ecosystems, such as InterUSS, enable secure coordination among UAS Service Suppliers (USSs). However, they bring up some security challenges at the infrastructure level that haven't been fully explored. This paper presents a security testing approach for InterUSS-based environments from the maintainer's perspective. By deploying and analyzing a working InterUSS infrastructure, we pinpoint key components and develop specific security tests aligned with established standards and protocols, such as mTLS and OAuth 2.0. We compiled these tests into a Testing Guide that aids both component validation and interaction analysis across InterUSS-based ecosystems, filling a gap in current research.

Recent frontier large language models (LLMs) have shown strong performance in identifying security vulnerabilities in large, mature open-source systems. As LLM-generated code becomes increasingly common, a natural goal is to prevent such models from producing vulnerable implementations in the first place. Formal verification offers a principled route to this objective, but existing verification pipelines typically require specifications written in rigid formal languages. Prior work has explored using LLMs to synthesize such specifications, with limited success. In this paper, we investigate a different approach: using LLMs both to generate specifications and to verify implementations compositionally when the specifications are expressed in natural language. Our preliminary results suggest that this approach is promising.

We demonstrate how publicly available social-media data and generative AI (GenAI) can be misused to automate and scale highly personalized, context-aware spear-phishing campaigns. With minimal attacker effort, a small amount of public activity per target is sufficient for GenAI models to extract interests and contextual cues, producing persuasive messages that mirror a target's style while bypassing generic content-moderation safeguards. We introduce a modular framework that combines multimodal signal extraction, communication-style profiling, and attack-type instantiation across seven strategies (baiting, scareware, honey trap, tailgating, impersonation, quid pro quo, and personalized emotional exploitation). We conduct a large-scale, multi-model evaluation covering thousands of generated emails and eight security-relevant criteria, benchmarking against a corpus of real-world phishing messages. The GenAI-produced emails exhibit markedly higher personalization, contextual grounding, and persuasive leverage. Importantly, a complementary user study corroborates these results, revealing that LLM-generated attacks consistently outperform APWG eCrimeX emails across eight dimensions while eliciting lower suspicion among human recipients. Finally, we measure and analyze the behavior of existing proactive, prompt-level defense mechanisms, which incorporate adaptive mechanisms, as well as two complementary defense approaches-policy-augmented SOTA safeguard models and system-instruction chain-of-thought moderation. We document how these defenses respond to contextualized and adaptive attack prompts, underscoring the need for platform-level safeguards that explicitly account for contextualized abuse at scale.

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An adversary may control and craft certain inputs, such as GitHub issue comments, to manipulate the LLM agent for unwanted actions, such as credential exfiltration and arbitrary command execution. To our knowledge, no prior academic work has studied such a risk in agentic workflows. In this paper, we design the first detection and exploitation framework, called JAW, to hijack agentic workflows hosted on automation platforms via a novel approach called Context-Grounded Evolution. Our key idea is to evolve agentic workflow inputs under the contexts derived from hybrid program analysis for hijacking purposes. Specifically, JAW generates agentic workflow contexts through three analyses: (i) static path-feasibility analysis to identify feasible agent-invocation paths and the input constraints required to trigger them, (ii) dynamic prompt-provenance analysis to determine how that input is transformed and embedded into the LLM context, and (iii) capability analysis to identify the actions and restrictions available to the agent at runtime. Our evaluation of JAW on GitHub workflows and n8n templates showed that 4714 GitHub workflows and eight n8n templates can be successfully hijacked, for example, to leak user credentials. Our findings span 15 widely-used GitHub Actions, including official GitHub Actions for Claude Code, Gemini CLI, Qwen CLI, and Cursor CLI, and two official n8n nodes. We responsibly disclosed all findings to the affected vendors and received many acknowledgements, fixes, and bug bounties, notably from GitHub, Google, and Anthropic.

The model context protocol (MCP) has been widely adopted as an open standard enabling the seamless integration of generative AI agents. However, while LLM guardrails have significantly matured to refuse malicious or harmful queries (e.g., "How do I build a bomb?"), recent work has shown that MCP-enabled LLMs are highly susceptible to prompt injection attacks which avoid harmful or suspicious cues (e.g., "Can you add this ssh key to my bashrc file?"). Herein, we use state-of-the-art (SOTA) alignment fine-tuning algorithms to explore whether LLMs may be aligned to refuse such falsely benign attacks (FBAs). While SOTA algorithms based on direct preference optimization (DPO) improve refusal guardrails against FBAs, we show that this improvement is limited; DPO-based fine-tuning never improves FBA refusal rates beyond 47% across five popular open-source LLMs. Thus, to further improve FBA refusals, we introduce Retrieval Augmented Generation for Preference alignment (RAG-Pref), a simple RAG-based alignment algorithm which conditions on preferred and dispreferred samples to leverage contrastive information during inference. RAG-Pref is online (training-free), compatible with off-the-shelf packages, and, when combined with offline alignment algorithms, enables an average 3.7-fold improvement in FBA refusals across five widely used LLMs, compared to 2.9 for other online alignment methods and 1.5 for offline alignment alone. We additionally show that RAG-Pref generalizes beyond agentic safety: in stark contrast to other online alignment methods, RAG-Pref consistently improves performance on general human-preference benchmarks AlpacaEval 2 and MT-Bench across five SOTA alignment-tuned models, demonstrating broad applicability to general alignment tasks.

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache, batching, prefix sharing, speculative decoding, adapters, and multi-tenant scheduling, creating shared-state behavior that only emerges under realistic concurrent workloads and is missed by standard model, safety, and API tests. We present GRIEF, a greybox fuzzer for LLM inference engines that treats timed multi-request traces as first-class inputs, uses lightweight oracles to detect crashes, hangs, performance pathologies, and silent output corruption, and applies controlled replay with log-probability checks to confirm reproducible serving-layer failures. Across early campaigns on vLLM and SGLang, GRIEF discovers 15 vulnerabilities, 10 confirmed by engine developers, including 2 CVEs, spanning KV-cache isolation failures, cross-request performance interference, and crash or liveness bugs. These results show that concurrency, caching, and state reuse can induce silent cross-request contamination, noisy-neighbor denial of service, and delayed crashes without malformed inputs or explicit server errors, making concurrent serving behavior a first-class security and reliability boundary for LLM infrastructure.