Papers

Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models (LLMs) by updating neural network layers using low-rank matrices. Since the generation of adversarial examples is an optimization process analogous to model training, this naturally raises the question: Do adversarial perturbations exhibit a similar low-rank structure? In this paper, we provide both theoretical analysis and extensive empirical investigation across various attack methods, model architectures, and datasets to show that adversarial perturbations indeed possess an inherently low-rank structure. This insight opens up new opportunities for improving both adversarial attacks and defenses. We mainly focus on leveraging this low-rank property to improve the efficiency and effectiveness of black-box adversarial attacks, which often suffer from excessive query requirements. Our method follows a two-step approach. First, we use a reference model and auxiliary data to guide the projection of gradients into a low-dimensional subspace. Next, we confine the perturbation search in black-box attacks to this low-rank subspace, significantly improving the efficiency and effectiveness of the adversarial attacks. We evaluated our approach across a range of attack methods, benchmark models, datasets, and threat models. The results demonstrate substantial and consistent improvements in the performance of our low-rank adversarial attacks compared to conventional methods.

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and systematic understanding of its security implications is increasingly important. Although a growing body of work has examined different attack surfaces and defense problems in agent systems, existing studies remain scattered across individual aspects of agent security, and there is still a lack of a layered review on this topic. To address this gap, this survey presents a layered review of security risks and defense strategies in autonomous agent frameworks, with OpenClaw as a case study. We organize the analysis into four security-relevant layers: the context and instruction layer, the tool and action layer, the state and persistence layer, and the ecosystem and automation layer. For each layer, we summarize its functional role, representative security risks, and corresponding defense strategies. Based on this layered analysis, we further identify that threats in autonomous agent frameworks may propagate across layers, from manipulated inputs to unsafe actions, persistent state contamination, and broader ecosystem-level impact. Finally, we highlight potential key challenges, including research imbalance across layers, the lack of long-horizon evaluation, and weak ecosystem trust models, and outline future directions toward more systematic and integrated defenses.

Access to genomic data is highly regulated due to its sensitive nature. While safeguards are essential, cumbersome data access processes pose a significant barrier to the development of AI methods for genomics. Synthetic data generation can mitigate this tension by enabling broader data sharing without exposing sensitive information. Synthetic genomic data are produced by training generative models on real data and subsequently sampling artificial data that preserves relevant statistics while limiting disclosures about the underlying individuals. In some settings, a single data holder may have sufficient data to train such generative models; however, in many applications data must be combined across multiple sites to achieve adequate scale. This need arises, e.g., in rare disease studies, where individual hospitals typically hold data for only a small number of patients. The solution we present in this paper enables multiple data holders to jointly train a synthetic data generator without revealing their raw data. Our approach combines secure multiparty computation (MPC) to ensure input privacy, so that no party ever discloses its data in unencrypted form, with differential privacy (DP) to provide output privacy by mitigating information leakage from the released synthetic data. We empirically demonstrate the effectiveness of the proposed method by generating high-utility synthetic datasets from multiple real RNA-seq cohorts in federated settings, showing that our approach enables privacy-preserving data synthesis even when data are distributed across institutions.

AI chatbots are becoming a primary interface for seeking information. As their popularity grows, chatbot providers are starting to deploy advertising and analytics. Despite this, tracking on AI chatbots has not been systematically studied. We present a systematic measurement of web tracking on 20 popular AI chatbots. Under controlled settings using a sensitive prompt, we capture and compare network traffic in normal chats and, where supported, private chats. We search for exposure of two categories of information: content, including prompts, prompt-derived titles, chat URLs, and chat identifiers; and identity, including names, emails, account identifiers, first-party cookies, and explicit IP/User-Agent fields in payloads. We find that 17 of 20 chatbots share information with at least one third party. Three chatbots share plaintext conversation text, including both prompt and response snippets, with Microsoft Clarity through session replay. Fifteen chatbots share conversation URLs or chat identifiers with third-party advertising, analytics, or social endpoints. Several chatbots expose user identity through support widgets, analytics, advertising, and session replay tags; in some cases, hashed emails are shared.

Federated learning (FL) is a popular distributed learning paradigm in machine learning, which enables multiple clients to collaboratively train models under the guidance of a server without exposing private client data. However, FL's decentralized nature makes it vulnerable to poisoning attacks, where malicious clients can submit corrupted models to manipulate the system. To counter such attacks, although various Byzantine-robust methods have been proposed, these methods struggle to provide balanced defense against multiple types of attacks or rely on possessing the dataset in the server. To deal with these drawbacks, thus, we propose an effective multi-layer defensive adaptive aggregation for Bzantine-robust federated learning (AdaBFL) based on a novel three-layer defensive mechanism, which can adaptively adjust the weights of defense algorithms to counter complex attacks. Moreover, we provide convergence properties of our AdaBFL method under the non-convex setting on non-iid data. Comprehensive experiments across multiple datasets validate the superiority of our AdaBFL over the comparable algorithms.

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local offline fine-tuning" is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive pretrained-weight poisoning attacks, while effective for natural language, fundamentally fail to capture such sparse high-entropy targets due to their reliance on probabilistic semantic prefixes. To bridge this gap, we identify and exploit a practical but overlooked supply-chain vector – malicious model code camouflaged as standard architectural definitions to realize a paradigm shift from passive weight poisoning to active execution hijacking. We introduce a deterministic full-chain memorization mechanism: it locks onto token-level secrets in dynamic computation flows via online tensor-rule matching, and leverages value-gradient decoupling to stealthily inject attack gradients, overcoming gradient drowning to force model memorization. Furthermore, we achieve, for the first time, attacker-verifiable secret stealing through black-box queries that precisely distinguishes true leakage from hallucination. Our attack achieves over 98% Strict ASR in the default LoRA setting with limited primary-task utility degradation and effectively evades defense measures including semantic safety filtering, code auditing, and perplexity-based detection.

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial attacks, especially whether such attacks transfer across different VLM architectures, is not well understood and poses a practical risk when attackers do not know which model a vehicle uses. We address this gap with a systematic cross-architecture study of adversarial transferability in VLM-based driving, evaluating three representative architectures (Dolphins, OmniDrive, and LeapVAD) using physically realizable patches placed on roadside infrastructure in both crosswalk and highway scenarios. Our transfer-matrix evaluation shows high cross-architecture effectiveness, with transfer rates of 73-91% (mean TR = 0.815 for crosswalk and 0.833 for highway) and sustained frame-level manipulation over 64.7-79.4% of the critical decision window even when patches are not optimized for the target model.

Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM platforms, and time-consuming manual triage workflows. We present an end-to-end threat management framework that integrates ensemble-based detection, syntax-constrained query generation, and retrieval-augmented resolution support to automate critical security workflows. Our detection module evaluates both traditional machine learning classifiers and large language models (LLMs), then combines the three best-performing LLMs to create an ensemble model, achieving 82.8% accuracy while maintaining 0.120 false positive rate on SIEM logs. We introduce the SQM (Syntax Query Metadata) architecture for automated evidence collection. It uses platform-specific syntax constraints, metadata-based retrieval, and documentation-grounded prompting to generate executable queries for IBM QRadar and Google SecOps. SQM achieves a BLEU score of 0.384 and a ROUGE-L score of 0.731. These results are more than twice as good as the baseline LLM performance. For incident resolution and recommendation generation, we demonstrate that integrating SQM-derived evidence improves resolution code prediction accuracy from 78.3% to 90.0%, with an overall recommendation quality score of 8.70. In production SOC environments, our framework reduces average incident triage time from hours to under 10 minutes. This work demonstrates that domain-constrained LLM architectures with retrieval augmentation can meet the strict reliability and efficiency requirements of operational security environments at scale.

Large Language Models (LLMs) have achieved remarkable progress in recent years, driving their adoption across a wide range of domains, including computer security. In reverse engineering, LLMs are increasingly applied to critical tasks such as function and variable name recovery and type inference. However, despite the rapid growth of research in this area, progress has been hindered by the absence of a standardized dataset. Existing studies rely on disparate datasets, preprocessing pipelines, and evaluation metrics, making fair comparisons between approaches difficult and obscuring a clear understanding of LLM capabilities in binary analysis. To address these challenges, we present REBench, a comprehensive benchmark dataset for evaluating LLMs on binary reverse engineering tasks. REBench consolidates a superset of existing datasets, comprising hundreds of millions of lines of source code and a diverse collection of binaries spanning multiple architectures and optimization levels. REBench adopts a knowledge-base-driven methodology that stores byte-level stack information to generate ground truth, ensuring that task difficulty is preserved while maintaining universal applicability. This design enables fair evaluation across tasks while avoiding simplifications that could bias results. As a use case, we apply REBench to measure the reverse engineering performance of LLMs and the result demonstrates difficulties in complex tasks.

Android residential proxy applications represent a growing class of potentially-unwanted programs (PUPs) that covertly route third-party traffic through end-user devices, enabling ad fraud, credential abuse, and evasion of geolocation controls by sophisticated threat actors. Attributing an unknown APK to a specific proxy network remains challenging due to code reuse, SDK embedding, and obfuscation across proxy families. We present a static-analysis pipeline for automated proxyware family attribution, extracting graph-structured representations (control-flow and function-call graphs) and behavioral signatures from a labeled corpus of 3,365 Android proxy apps spanning four commercial proxy networks. We evaluate Weisfeiler-Lehman graph kernel features alone and fused with binary capability vectors across multiple classifiers. Using 5-fold DEX-grouped cross-validation to prevent data leakage, SGD achieves a macro F1 of 0.985 on the expanded dataset. To support explainability, we map classifier decisions to automatically generated Yara rules, achieving per-family accuracies up to 88.45% after filtering non-discriminative signatures. Finally, we discuss these results in the context of the broader ecosystem. We find that from the expanded dataset, the majority of applications (51.4%) still available through APKPure still contain embedded proxy SDK code. Further analysis of developer accounts reveals that 23 developers are responsible for other applications also containing such functionality, suggesting continuous and ongoing commercial relationships between proxy providers and developers.

Quantum secret sharing schemes are a family of quantum cryptographic protocols which provide secure quantum encodings, mapping one secret to multiple shares of information such that the original secret cannot be accessed without an authorized set of shares present for decoding. In this work, we describe a protocol that enables sender-anonymity during the secret decoding process. By using permutation-invariant QEC codes along with a set of anonymous quantum transmission algorithms, we construct a quantum anonymous secret sharing scheme that achieves sender-anonymity. We quantify information leakage in ramp quantum secret sharing schemes via the quantum conditional min-entropy, justifying it as a valid measure of leaked information by relating it to the Knill-Laflamme quantum error correction conditions. Finally, we evaluate several permutation-invariant codes using this measure to make observations on the information leakage of intermediate shares for each quantum anonymous secret sharing scheme.

Large Language Model (LLM) agents are increasingly proposed to automate offensive security tasks, with recent studies reporting near human-level success rates in Capture-the-Flag (CTF) challenges. We here revisit these results, providing a second look at these claims. We engineer different agent architectures of increasing complexity and modularity on 30 web-based CTFs challenges spanning 14 vulnerability classes. We instantiate these agents with multiple LLM backbones, and compare them with claude-code, a general-purpose agent that automatically determines its internal architecture. Our evaluation yields three main findings. First, claude-code achieves performance comparable to the engineered architectures (19/30 solved tasks), suggesting that general-purpose agents are strong baselines for offensive security tasks. Second, both our architectures and claude-code struggle in the same challenge categories, revealing persistent barriers that keep current agents below human-level capability. Third, by leveraging our manually designed architectures we can systematically measure the impact of additional components, finding that structured orchestration of specialized roles outperforms monolithic designs, improving run-to-run consistency, and reducing execution costs.

We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, overwrote a system registry, overrode a prior negative decision from an oversight agent, and escalated through increasingly privileged operations up to an attempted system administrator command. The incident was preceded not by an adversarial attack but by routine content: a forwarded technology article written for human developers and shared by the principal investigator for discussion. The agent operated in a permissive environment, with unrestricted shell access, soft behavioral guidelines containing genuinely conflicting instructions, and no machine-enforced installation policy, and had recommended installing the same tool six hours earlier before being told to stand down. We analyze the behavioral cascade, the control boundaries that failed, and the limitations of multi-agent oversight in detecting and remediating the damage. We use directive weighting error as a descriptive interpretation of the observed failure and ambient persuasion as a provisional analytic label for the broader trigger configuration of non-adversarial environmental content preceding unauthorized agent action. The case highlights ethical and governance implications for deployed agent systems: ambiguous conversational cues are insufficient authorization for consequential actions, prior refusals must persist as enforceable constraints rather than message-level reminders, and oversight mechanisms require systematic post-incident auditing in addition to routine monitoring.

As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physical-world consequences. Although prior work has studied robotic cybersecurity, adversarial perception attacks, and LLM safety independently, no existing study traces how these threat categories interact and propagate across trust boundaries in a unified architectural model. We address this gap by modeling an LLM-enabled autonomous robot in an edge-cloud architecture as a hierarchical Data Flow Diagram and applying STRIDE-per-interaction analysis across six boundary-crossing interaction points using a three-category taxonomy of Conventional Cyber Threats, Adversarial Threats, and Conversational Threats. The analysis reveals that these categories converge at the same boundary crossings, and we trace three cross-boundary attack chains from external entry points to unsafe physical actuation, each exposing a distinct architectural property: the absence of independent semantic validation between user input and actuator dispatch, cross-modal translation from visual perception to language-model instruction, and unmediated boundary crossing through provider-side tool use. To our knowledge, this is the first DFD-based threat analysis integrating all three threat categories across the full perception-planning-actuation pipeline of an LLM-enabled robotic system.

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently lack security verification and are highly susceptible to data poisoning attacks. Such poisoning can cause models to generate syntactically valid but insecure hardware modules that bypass standard functionality checks. To address this, we present SafeTune, a framework designed to harden LLM-based RTL generation against poisoning, specifically focusing on hardware Trojan (HT) insertion. SafeTune integrates two core components: (i) a Graph Neural Network (GNN) that models structural properties to identify anomalous circuitry patterns during fine-tuning, and (ii) a semantic verification module using text embeddings and an XGBoost classifier to assess prompt security. By coupling structural and semantic knowledge, SafeTune effectively filters poisoned inputs without sacrificing legitimate data. Experimental results demonstrate that SafeTune significantly enhances the robustness and reliability of LLM fine-tuning without requiring modifications to the underlying model architecture.

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries to embed instructions directly in web resources, i.e., indirect prompt injections. While prior work demonstrates such attacks in controlled settings, their prevalence, deployment, and real-world impact remain unclear. We present one of the first large-scale empirical analyses of indirect prompt injections in webpages and HTTP responses. Analyzing 1.2B URLs from 24.8M hosts, we identify 15.3K validated instances across 11.7K pages. These are not isolated cases: a small number of recurring templates account for most cases. We characterize their objectives, delivery mechanisms, visibility, persistence, and impact, revealing a heterogeneous ecosystem spanning disruptive prompts, reputation manipulation, content-protection directives, and AI-bot detection, targeting systems such as crawlers, search pipelines, customer-support agents, and hiring workflows. A key finding is that most instructions target machines rather than humans: about 70% appear in non-rendered HTML (e.g., headers, comments, metadata), and many visible cases are hidden via rendering techniques. To assess practical risk, we run 5,200 controlled experiments across 13 models and four webpage representations. Our results show compliance is limited but non-negligible, reaching up to 8% for smaller models on plain-text inputs, while structured representations reduce compliance by preserving structural cues. Overall, prompt-based interference is already present in the web ecosystem and represents a growing source of tension between LLM-driven automation and the sites it consumes.

While current network intrusion detection systems achieve satisfactory accuracy, they often lack explainability. Subgroup Discovery (SD) addresses this by building interpretable rules that characterize feature interactions associated with attack traffic. With large datasets, classical heuristic beam search methods struggle with exponentially scaling search spaces and can prune critical multi-feature interactions. This paper introduces a quantum-enhanced pipeline for SD applied to network intrusion detection using NSL-KDD, formulating SD as quantum optimization for the first time. By encoding feature selection as a Quadratic Unconstrained Binary Optimization (QUBO) and solving it via the Quantum Approximate Optimization Algorithm (QAOA) on IBM Quantum hardware (ibm_pittsburgh), the pipeline identifies subgroups of network features that discriminate normal from attack traffic. A least-squares regression QUBO formulation fits the Weighted Relative Accuracy (WRAcc) landscape over feature subsets, with surrogate sampling for larger QUBOs. Results are benchmarked against exhaustive enumeration and Beam Search using ratios for Hamiltonian quality and WRAcc. Hardware scaling experiments on ibm_pittsburgh (10-30 qubits) reveal that QAOA at depth p = 1 shows WRAcc ratios of 0.983 at 10 qubits, 0.971 at 15 qubits, 0.855 at 20 qubits, and 0.624 at 25 qubits, degrading to 0.039 at 30 qubits as circuit noise dominates, establishing an empirical NISQ scaling boundary. Results demonstrate that QAOA discovers subgroups competitive with classical heuristics and finds multi-feature interaction patterns that greedy Beam Search prunes, with QAOA-unique subgroups achieving up to 99.6% test precision. This work establishes a framework for quantum combinatorial optimization in cybersecurity and characterizes hardware scaling for NISQ devices.

Cloud-based Large Language Models (LLMs) can perform autonomous penetration-testing sub-tasks such as Linux privilege escalation, but raise security, privacy, and sovereignty concerns. Locally hosted open-weight models avoid these issues, yet prior work reports that small open-weight models succeed on only 8-16% of standardized privilege-escalation tasks, far below frontier cloud models. This paper is an empirical study of why small models fail at this task and which engineering techniques close the gap. From execution traces we distill six recurring failure modes, map each to an established enhancement technique, and evaluate five (chain-of-thought prompting, retrieval-augmented generation, structured prompting, history compression, and reflective analysis) as reproducible extensions to the open-source hackingBuddyGPT framework. Under a single shared harness and matched conditions, the set of techniques we evaluate raise two SLMs (Llama3.1 8B, Qwen2.5 7B) from 8% to 67% with guidance, matching guided GPT-4o. A larger open-weight reference model (Llama3.1 70B) reaches 83%. A full-factorial ablation shows that reflection-based techniques contribute most and reveals vulnerability discovery, not exploitation, as the main constraint for local models. We report these as transferable lessons for building reliable local offensive agents as well as to inform defenders.

Safety-aligned language models must refuse harmful requests without broad over-refusal, but it remains unclear how dynamic adversarial fine-tuning changes refusal-control carriers: Kullback–Leibler (KL)-constrained directions or small subspaces that causally modulate refusal without large safe-prompt distribution shifts. We study a 7B backbone under supervised fine-tuning (SFT) and Robust Refusal Dynamic Defense (R2D2), aligning HarmBench, StrongREJECT, and XSTest evaluations with five-anchor geometry measurements, causal interventions, and sparse adaptive stress tests. R2D2 drives fixed-source HarmBench attack success to zero at early checkpoints; however, these checkpoints also exhibit maximal XSTest refusal and fail a benign-utility audit. Later checkpoints partially recover utility-facing behavior while reopening attack success, with adaptive GCG attack success rate rising to 0.415 at step 250 and 0.613 at step 500. Internally, R2D2 preserves a late-layer admissible refusal-control carrier through step 100 and then relocates the best admissible carrier to an early layer; SFT relocates earlier yet remains less robust. Effective rank stays near 1.24, and SFT shows larger principal-angle drift, arguing against both dimensional expansion and drift magnitude as sufficient explanations. Causal interventions support a low-dimensional but utility-coupled carrier. These results support a geometry-reorganization account of R2D2 along a robustness–utility frontier, without establishing adaptive robustness.

The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning models. Privacy regulations restrict data sharing, making synthetic data generation a promising alternative. The use of Large Language Models (LLMs) in a data augmentation pipeline could be leveraged as an alternative in this field. In the proposed methodology, DeepSeek-R1, OpenBioLLM-Llama3 and Qwen 3.5 are used to generate synthetic mental health evaluation reports conditioned on specific International Classification of Diseases, Tenth Revision (ICD-10) codes. Because naive text generation can lead to mode collapse or privacy breaches (memorization), a comprehensive evaluation framework is introduced. The generated diagnostic texts are assessed across three dimensions: semantic fidelity, lexical diversity, and privacy/plagiarism. The results demonstrate that all models can generate clinically coherent, diverse, and privacy-safe synthetic reports, significantly expanding the available training data for clinical natural language processing tasks without compromising patient confidentiality.

Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video–text corpora collected from heterogeneous sources, raising an immediate privacy question: can an external auditor determine whether a particular video was used during training? While membership inference attacks (MIAs) have been studied extensively for classifiers and, more recently, for text and image generation models, the VideoLLM setting remains unexplored. This setting is challenging because black-box auditors observe only generated text, whereas the membership signal is entangled with video-specific factors such as motion complexity and temporal span. In this paper, we present a black-box MIA targeting VideoLLMs that couples temperature-perturbed generation with video-aware difficulty features. Our key intuition is that member samples tend to induce sharper, more brittle generation behavior across decoding temperatures, and that this signal should be interpreted jointly with the intrinsic difficulty of the queried video. Concretely, we query the target model at low and high temperatures, measure the semantic drift between the resulting texts. We evaluate the attack against LLaVA-Video-7B-Qwen2-Video-Only and achieve a member inference AUC of 0.68 and accuracy of 0.63. These results demonstrate that Video-LLMs are vulnerable to black-box membership inference attacks, highlighting an urgent need for the community to systematically evaluate and mitigate privacy risks in VideoLLMs.

Developers and organizations are using Large Language Models (LLMs) to generate security-critical code more frequently than ever, including cryptographic solutions for their products. This study presents an empirical evaluation of cryptographic security in 240 Rust code samples for two crypto algorithms (AES-256-GCM and ChaCha20-Poly1305) generated by three LLMs (Gemini 2.5 Pro, GPT-4o, and DeepSeek Coder) using four different prompt strategies. For each successfully compiled code sample, CodeQL static analysis and our rule-based crypto-specific analyzer were used to detect vulnerabilities, which are also associated with Common Weakness Enumeration (CWE). The evaluation results revealed that only 23.3% of the generated code samples were successfully compiled. Among the compiled code, CodeQL produced only two false positives, while our rule-based crypto-specific analyzer identified vulnerabilities in 57% of the compiled samples with zero false positives. This demonstrates that general-purpose analysis tools are insufficient for code validation for the experimented crypto algorithms. The compilation success of the two algorithms varied significantly (AES-256-GCM 34.2% versus ChaCha20-Poly1305 12.5%), showing a gap in code generation capabilities. While model choice had no significant effect on compilation success, prompt strategy significantly influenced outcomes (P = 0.002), with chain-of-thought prompting performing 5 times worse than zero-shot. All three models exhibit systematic failures, including nonce reuse and API hallucinations.

Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional static and dynamic analysis tools provide valuable structural and behavioral insights, yet they often operate in non-adaptive workflows and produce large volumes of warnings requiring manual triage. Feedback-driven fuzzing and search-based testing approaches have demonstrated the power of iterative input refinement guided by execution signals, while large language models (LLMs) have shown promise in automated test generation but frequently lack semantic grounding in program structure. This paper presents a systematic survey of adaptive and AI-augmented security testing research across five domains: (1) structural program analysis for vulnerability detection, (2) DevSecOps and continuous security testing, (3) feedback-driven fuzzing and search-based testing, (4) LLM-based automated test generation, and (5) emerging hybrid systems integrating program analysis with adaptive learning. We analyze fifty-five peer-reviewed studies drawn from a systematic search of four major databases yielding 22,088 raw records. Our analysis reveals a persistent disconnect between structural program representations (ASTs, CFGs, and CPGs) and adaptive testing mechanisms. We characterize this as structural-adaptive fragmentation: a systematic separation that neither paradigm individually addresses. No existing system incorporates human triage signals as feedback for refining structural models. We conclude by identifying five open research challenges and outlining a unified agenda for semantically grounded, feedback-driven, polyglot security testing frameworks.

Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance. Current deployments frequently lack (1) uniform agent discovery, (2) cryptographic agent authentication, (3) capability proofs that protect secrets, and (4) enforceable policy controls. This paper presents an implementation-oriented proof of concept for the Agent Name Service (ANS), a DNS-inspired trust layer for AI agent discovery and interoperability in Kubernetes, grounded in the ANS protocol specification~\cite{huang2025ans}. The implementation uses Decentralized Identifiers (DIDs), Verifiable Credentials (VCs), policy-as-code enforcement with Open Policy Agent (OPA), and Kubernetes-native integration patterns (CRDs, admission controls, service mesh integration). In a demo research environment (3-node cluster, 50-agent workflow simulation), we observe sub-10ms response in demonstrated service paths and full success for scripted demo deployment scenarios. We explicitly scope these findings as proof-of-concept evidence rather than production certification. We further provide a threat model, assumptions, and limitations to separate implemented evidence from protocol-defined and roadmap capabilities. The result is an evidence-grounded pathway from ANS protocol concepts to reproducible engineering practice for secure multi-agent systems.

FlyClient is a lightweight blockchain verification protocol that enables proof-of-work validation using minimal data, making it ideal for resource-constrained environments like mobile wallets, Internet-of-Things devices or cross-chain bridges implemented with smart contracts. Despite its strong potential for enabling lightweight blockchain verification, FlyClient protocol is still in the experimental stages, with limited real-world deployments and performance evaluations under diverse conditions. In this paper we bridge the gap between theory and deployment, by addressing several technical challenges to advance FlyClient to a production-ready solution. Namely, our contribution is three-fold: (i) we formally introduce an adversary model alternative to the original FlyClient one, that allows us to parametrize a verifier under a concrete economic interpretation, while also saving some proof space; (ii) we provide the first practical FlyClient prover implementation for a production blockchain (Zcash), and we estimate its performance under different configurations; (iii) we introduce and evaluate two optimizations that minimize the size of FlyClient proofs, the first of which does not require any consensus change.

Scalar multiplication kP is a critical operation in Elliptic Curve Cryptosystems (ECC), often targeted by Side-Channel Analysis (SCA). Despite strategies based on atomic patterns to enhance security, the binary kP algorithms remain susceptible to simple SCA due to energy consumption variations in field multipliers during passing two different or two identical operands. This vulnerability arises independent of the multiplication method used. We implemented and analysed two mitigation techniques: one involving data redirection and another focusing on bus reloading.

Retrieval-Augmented Generation (RAG) is essential for enhancing Large Language Models (LLMs) with external knowledge, but its reliance on cloud environments exposes sensitive data to privacy risks. Existing privacy-preserving solutions often sacrifice retrieval quality due to noise injection or only provide partial encryption. We propose PRAG, an end-to-end privacy-preserving RAG system that achieves end-to-end confidentiality for both documents and queries without sacrificing the scalability of cloud-hosted RAG. PRAG features a dual-mode architecture: a non-interactive PRAG-I utilizes homomorphic-friendly approximations for low-latency retrieval, while an interactive PRAG-II leverages client assistance to match the accuracy of non-private RAG. To ensure robust semantic ordering, we introduce Operation-Error Estimation (OEE), a mechanism that stabilizes ranking against homomorphic noise. Experiments on large-scale datasets demonstrate that PRAG achieves competitive recall (72.45%-74.45%), practical retrieval latency, and strong resilience against graph reconstruction attacks while maintaining end-to-end confidentiality. This work confirms the feasibility of secure, high-performance RAG at scale.

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.

As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat to scholarly integrity. We propose SafeReview, a co-evolutionary adversarial training framework for defending LLM-based peer review systems against such attacks. SafeReview jointly trains a Generator model to create sophisticated attack prompts and a Defender model to preserve review integrity under adversarial manipulation. The Generator is optimized to produce increasingly effective prompt injections, while the Defender is strengthened through preference-based training to maintain consistent reviews between clean and attacked submissions. Experimental results show that SafeReview improves robustness against adaptive prompt injection attacks, better preserves paper ranking under attack, and generalizes across attacker architectures compared with static defenses. These results demonstrate the potential of co-evolutionary training as a foundation for securing LLM-assisted peer review.

Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quantization offline, dynamic quantization operates on tensors at run-time, adapting its parameters to the actual input data. Today's mainstream machine learning frameworks, including ML compilers and inference engines, frequently recommend dynamic quantization as an initial step for optimizing model serving. This is because dynamic quantization can significantly reduce memory usage and computational load, leading to faster token generation and improved model serving efficiency without substantial loss in model accuracy. In this paper, we reveal a critical vulnerability in dynamic quantization: an adversary can exploit such quantization strategy to steal sensitive user data placed in the same batch as the adversary's input. Our analysis demonstrates that dynamic quantization, when improperly implemented or configured, can create side channels that expose information about other inputs within the same batch. We call this phenomenon Quantamination, describing contamination from quantization. Specifically, we show that at least 4 of the most popular ML frameworks in use today either default to or can use configurations that leak data across the batch boundary. This data leakage, in theory, allows attackers to partially or even fully recover other users' batched input data, representing a serious privacy risk for existing ML serving frameworks.