281 papers
This paper proposes and evaluates an on-premises collaborative framework utilizing multiple large language models with majority voting to efficiently and privately identify cryptographically relevant software packages, thereby addressing the challenges of manual inventory and static analysis limitations in the transition to post-quantum cryptography.
This paper proposes the Layered Governance Architecture (LGA), a four-layer framework designed to systematically mitigate execution-layer vulnerabilities in autonomous agent systems, and validates its effectiveness through a bilingual benchmark demonstrating high interception rates of malicious tool calls with minimal latency.
This paper introduces aCAPTCHA, a novel security protocol that verifies whether an entity is a capable AI agent by leveraging the asymmetric processing speed between humans and machines to solve the Agentic Capability Verification Problem (ACVP) through time-constrained, multi-round natural language challenges.
The paper introduces mAVE, a novel watermarking framework that cryptographically binds audio and video latents in joint generation models to eliminate the "Binding Vulnerability" of existing methods and robustly defend against adversarial Swap Attacks without requiring model fine-tuning.
This paper demonstrates that leveraging eBPF-based system-level monitoring reveals new leakage patterns in Searchable Symmetric Encryption (SSE) that extend beyond traditional threat models, thereby enabling more powerful leakage abuse attacks and highlighting the critical need to address system-level exposures in SSE defenses.
This paper introduces TFM, a temporal attack framework that exploits the vulnerability of text-to-video models to generate harmful content by providing only sparse boundary conditions (start and end frames) and implicitly substituting sensitive cues, thereby bypassing existing safety filters and significantly increasing jailbreak success rates.
This paper proposes an extended Consent-Based Access Control framework that enhances patient autonomy and system performance by shifting conflict resolution to a pre-commit validation phase, formalizing immutable access invariants, and implementing a context-aware emergency mechanism that balances clinical continuity with strict data privacy.
This paper proposes and formally evaluates a privacy-preserving, patient-centric identity management framework that ensures secure healthcare access by balancing operational reliability with strong protections against linkability and traceability through anonymous pseudonyms and conditional traceability.
This review paper analyzes the dual threats posed by quantum computing and artificial intelligence to current cryptographic systems, concluding that a comprehensive defense requires a dynamic, multi-layered strategy combining post-quantum algorithms, implementation hardening, and cryptographic agility to address the limitations of any single solution.
The paper presents pqRPKI, a practical post-quantum RPKI framework that utilizes a multi-layer Merkle Tree Ladder and a redesigned manifest structure to significantly reduce bandwidth and validation costs compared to naive post-quantum signature swaps, while enabling efficient dual-stack deployment with minimal overhead.
Space-Control is a hardware-software co-design that addresses the critical security gap of missing process-level isolation in CXL-based disaggregated memory by authenticating execution contexts and enforcing fine-grained access control with minimal performance overhead.
This paper presents a comprehensive systematization of knowledge on Self-Sovereign Digital Identities (SSDI) by analyzing 80 sources to identify six major adoption challenges, evaluating 47 academic publications and 12 real-world applications to reveal that self-sovereignty is a spectrum, and outlining future research directions to accelerate the shift from centralized to self-sovereign identity systems.
This paper presents SDN-SYN PoW, an adaptive defense architecture that leverages a Software-Defined Networking controller to dynamically adjust non-interactive Proof-of-Work difficulty based on real-time traffic analysis, effectively mitigating multi-domain SYN floods while maintaining negligible overhead for legitimate clients.
The paper introduces RedSage, an open-source, locally deployable cybersecurity LLM trained on a massive curated dataset and agentic augmentation pipeline, which achieves state-of-the-art performance on specialized cybersecurity benchmarks while also improving general reasoning capabilities.
This paper introduces IAG, the first input-aware backdoor attack on vision-language models for visual grounding, which utilizes a text-conditioned UNet to dynamically generate imperceptible, target-specific triggers that achieve high attack success rates across various models and datasets while maintaining stealth and robustness against defenses.
This paper introduces SlowBA, a novel backdoor attack against VLM-based GUI agents that utilizes a two-stage reward-level injection strategy and realistic pop-up triggers to induce excessive reasoning chains, thereby significantly increasing response latency while maintaining task accuracy and evading existing defenses.
The paper introduces DistillGuard, a framework that systematically evaluates output-level defenses against LLM knowledge distillation and finds that most current approaches are largely ineffective, with performance degradation being highly task-dependent and insufficient to broadly prevent knowledge theft.
This Systematization of Knowledge (SoK) paper establishes the first unified framework for Agentic Retrieval-Augmented Generation (RAG) by formalizing autonomous loops as decision-making processes, proposing a comprehensive taxonomy and architectural decomposition, critiquing current evaluation limitations and systemic risks, and outlining critical research directions for building reliable and scalable agentic systems.
This paper presents a toolkit leveraging Large Language Models to automate key aspects of Artifact Evaluation in cybersecurity research, achieving high accuracy in reproducibility rating, autonomous environment setup, and pitfall detection to significantly reduce reviewer effort and enhance research transparency.
This paper identifies and formalizes "Retrieval Pivot Attacks" in Hybrid RAG systems, demonstrating how vector-retrieved seeds can inadvertently pivot through knowledge graph links to cause cross-tenant data leakage, and proves that enforcing authorization specifically at the graph expansion boundary effectively mitigates this risk with minimal overhead.