10 papers · 1 filter
Measuring Safety Alignment Effects in Autonomous Security Agents
Isaac David, Arthur Gervais
Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Single-turn refusal benchmarks ca…
Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
Isaac David, Arthur Gervais
Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation am…
Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches
Isaac David, Arthur Gervais
Security updates create a short but important window in which defenders and attackers can compare vulnerable and patched software. Yet in many operational settings, the most access…
Alignment Contracts for Agentic Security Systems
Isaac David, Marco Guarnieri, Arthur Gervais
Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the syste…
Towards Optimal Agentic Architectures for Offensive Security Tasks
Isaac David, Arthur Gervais
Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and…
TxRay: Agentic Postmortem of Live Blockchain Attacks
Ziyue Wang, Jiangshan Yu, Kaihua Qin +3
Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but this openness exp…
Multi-Agent Penetration Testing AI for the Web
Isaac David, Arthur Gervais
AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing. Wi…
AI Agent Smart Contract Exploit Generation
Arthur Gervais, Liyi Zhou
Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with c…
Decompiling Smart Contracts with a Large Language Model
Isaac David, Liyi Zhou, Dawn Song +2
The widespread lack of broad source code verification on blockchain explorers such as Etherscan, where despite 78,047,845 smart contracts deployed on Ethereum (as of May 26, 2025),…
AuthorMist: Evading AI Text Detectors with Reinforcement Learning
Isaac David, Arthur Gervais
In the age of powerful AI-generated text, automatic detectors have emerged to identify machine-written content. This poses a threat to author privacy and freedom, as text authored…