Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks

Large language model LLM agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22...

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to...

Exploit for Origin Validation Error in Ultraviolet Cocos_Ai

DugganUSA — IETF Hackathon Contributions Real-world threat-in...

Mythos Didn't Break Your Security Program. Your Exposure Window Could.

The industry spent the initial months after Anthropic's April 7 Mythos reveal focused on volume. How many new CVEs would Mythos add to an already overloaded pipeline? How quickly would the flood of AI-driven discovery overwhelm triage capabilities? How long would it take adversaries to weaponize...

SingGuard-NSFA: Extensible Guardrails for Agentic AI Via Generative Reasoning and Real-Time Classification

We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185...

kang-lab-starter-task

Starter task: designing tasks Fable Claude Code and GPT-5.6...

Using LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques

Static analysis is widely used for finding security weaknesses in source code before deployment, but it often produces far more alerts than analysts can review. We study how well large language models LLMs can adjudicate classify as a real bug or a false alarm static-analysis alerts. We use two...

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents

Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was. We introduce an...

From Regression to Prior-Aware Inference: Solving the ILWE Family in Randomness Leakage Attacks against ML-DSA

ML-DSA is a representative lattice-based signature scheme standardized by NIST. It relies on signing randomness and rejection sampling to ensure that released signatures are statistically independent of the secret key. Practical implementations, however, may leak partial information about this...

Conductance-Repair Evidence Graphs for Prospective Security Retrieval

Security retrieval is often evaluated as ranking over complete evidence, but operational triage is prospective: CVE descriptions, weakness metadata, fix commits, EPSS scores, KEV membership, validation-vector metadata, and side-channel benchmark routes arrive through separate channels, and many a...

Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions

The rapid growth of publicly available digital information has rendered manual open-source intelligence OSINT analysis insufficient for modern intelligence, cybersecurity, and cyber investigation. Large language models LLMs and agentic AI systems, capable of tool use, multi-step reasoning, and...

Enhanced Feature Extraction for IoT Network Intrusion Detection Using GNNs and KAN

Recent advancements in the Internet of Things IoT emphasize the urgent need for advanced network security, as IoT networks feature dynamic topologies, imbalanced traffic, and complex attack patterns. Unlike general IT networks, IoT environments exhibit extreme heterogeneity and sparse topologies...

arline-benchmarks (>=0.1.4, <=0.1.8), arline-quantum (>=0.1.4, <=0.1.8) potentially affected by CVE-2025-2000 via qiskit (0.18.3)

qiskit PYPI version 0.18.3 is affected by a known vulnerability. The following packages have a transitive dependency on qiskit and may be impacted: - arline-benchmarks =0.1.4, =0.1.4, =0.1.8 Source cves: CVE-2025-2000 Source advisory: OSV:PYSEC-2026-510...

Reinforcement Learning for Software Vulnerability Analysis: A Systematic Review with Emphasis on C/C++ Source Code and Static Analysis

Vulnerability detection in C/C++ software remains a major security challenge due to code complexity, manual memory management, and the limitations of traditional static analysis. Reinforcement Learning RL has emerged as a promising approach, particularly for fuzzing, test generation, program...

ai-goat-ai-vulnerability-exploits-collection

AI GOAT - AI Vulnerability & Exploits Collection ⚠️ A del...

DISARM: Target Electronic Device Informed Mitigation of Software Runtime Side-Channel Vulnerabilities

Program runtime or timing attacks exploit variations in a program's execution times to extract sensitive information from the program e.g. encryption keys, sensitive variable data, intellectual property. State-of-the-art solutions to runtime side-channel attacks attempt to balance the execution...

AttackonCTF: Defending Hardware Security Competition Benchmarks in the Age of LLMs

Hardware security competitions such as HackTheSilicon serve as benchmarking platforms for evaluating vulnerability detection methods and for training humans and AI. However, our study reveals that LLMs threaten their validity. Instead of genuine security reasoning, detectors exploit a diff-style...

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Hierarchical multi-agent systems MAS are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particular...

InjectV: Modeling Fault Injection Attacks in RISC-V Simulation Environment

Fault Injection Attacks FIAs are a significant threat to hardware security, capable of compromising systems by inducing malicious faults in computation or storage. Evaluating resilience against such attacks is challenging due to the high cost, complexity, and limited availability of physical faul...

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five terminal-agent benchmarks and find 323 16% hackable by frontier models given only the task description. This corrupts both...