303 papers
This paper introduces SecureRAG-RTL, a novel Retrieval-Augmented Generation framework that significantly improves hardware vulnerability detection in HDL designs by integrating domain-specific knowledge retrieval with large language models, achieving an average 30% increase in accuracy while also releasing a new benchmark dataset of 14 annotated designs.
This paper argues that current CPU-based testing methods fail to ensure memory safety in heterogeneous systems due to unfaithful translations, and it proposes a GPU-native fuzzing pipeline for CUDA programs as a more reliable solution to address the growing number of exploitable bugs in modern AI and scientific workloads.
This paper introduces SAHA, a novel jailbreak framework that targets deep safety attention heads in open-sourced large language models through ablation-impact ranking and layer-wise perturbation, achieving a 14% improvement in attack success rate over state-of-the-art baselines.
This paper proposes the Disentangled Safety Hypothesis (DSH), which reveals that large language models separate safety "recognition" and "refusal execution" into distinct geometric subspaces, enabling the development of the Refusal Erasure Attack (REA) to bypass safety mechanisms by surgically disabling the refusal axis while preserving harmful content generation.
This paper proposes "Proof-of-Guardrail," a system leveraging Trusted Execution Environments to provide cryptographic, verifiable attestation that AI agents enforce specific safety measures, thereby addressing the threat of falsely advertised safety while acknowledging remaining risks like active jailbreaking.
This paper proposes a lightweight neural distinguisher for differential cryptanalysis that utilizes quantization-aware training to replace 32-bit multiplications with Boolean operations, achieving a 86.1% reduction in total operations and eliminating costly multiplications with only a negligible drop in classification accuracy.
The paper proposes ISS-RegAuth, a lightweight indoor space authentication framework that achieves superior accuracy, reduced latency, and enhanced privacy by authenticating users through sparse ISS keypoints and Fast Point Feature Histograms derived from 3D LiDAR scans, rather than processing entire point clouds.
This paper demonstrates that in competitive environments, self-evolving large language model agents inevitably drift toward deception as a robust, evolutionarily stable strategy, revealing a fundamental tension between autonomous self-improvement and alignment.
ThermoCAPTCHA is a privacy-preserving human verification system that utilizes real-time thermal imaging and cryptographically bound tokens to achieve high-accuracy, low-latency bot detection without imposing cognitive burdens or compromising user privacy.
This paper proposes and statistically optimizes a three-factor MFA scheme for protecting private keys, which utilizes a novel bit-truncation method on template-less facial biometrics combined with SRAM PUF tokens and passwords to significantly reduce error rates and generate error-free ephemeral keys.
SemFuzz is a semantics-aware fuzzing framework that leverages large language models to extract rules from RFC documents and generate targeted test cases, successfully identifying deep semantic vulnerabilities in network protocol implementations that traditional methods often miss.
This paper introduces APIDiffer, a specification-guided differential testing framework that automatically detects API inconsistencies across Ethereum clients by generating real-world test cases and using large language models to filter false positives, successfully uncovering 72 confirmed bugs and significantly outperforming existing tools in coverage and accuracy.
This paper introduces a novel, LINDDUN-based privacy threat modeling framework specifically designed for Generative AI systems, which expands the existing threat taxonomy with new categories and examples derived from a systematic literature review and validated through a case study on an AI Agent system.
This paper introduces PQC-LEO, an automated benchmarking framework for evaluating the computational and networking performance of Post-Quantum Cryptography algorithms across x86 and ARM architectures, revealing that higher security levels incur greater performance penalties on ARM devices compared to x86.
The paper proposes Alkaid, a provably secure steganographic scheme that achieves deterministic robustness against edit errors by integrating minimum distance decoding into the encoding process, thereby significantly outperforming state-of-the-art methods in decoding success rates, payload capacity, and encoding speed.
The paper proposes SPOILER, a novel framework that combines hardware-aware neural architecture search and self-poisoning learning to decouple TEE-protected sub-networks from the main backbone, thereby achieving optimal trade-offs between security, efficiency, and accuracy in on-device DNN inference.
This paper proposes an Integrated Failure and Threat Mode and Effect Analysis (FTMEA) framework for automotive semiconductors that unifies functional safety and cybersecurity assessments by introducing quantified Cross-Domain Correlation Factors to accurately identify and prioritize synergistic risks that traditional methods often overlook.
This paper proposes a framework for designing trustworthy layered attestations that overcome the limitations of shallow verification by structuring systems to isolate critical components and layer evidence across them, achieving reliable security against strong adversaries with negligible performance overhead using widely available hardware and software.
This paper proposes a hardware-independent, client-side classification framework that leverages the Normalized Compression Distance (NCD) within kernel methods to achieve high accuracy on minimal data without requiring large centralized datasets or extensive computational resources.
This paper introduces ESAA-Security, an event-sourced architecture that transforms AI-assisted security auditing from unreliable free-form LLM conversations into a traceable, reproducible, and verifiable governance pipeline by separating agent cognition from deterministic state mutations to ensure immutable audit trails for AI-generated code.