New research on AI and security, selected for relevance to language models, AI agents and cybersecurity. Summaries are the authors’ or publisher’s own words, linked to the original.
Peer-reviewed
Improving molecular property prediction with score-based diffusion models
New preprints (not yet peer-reviewed)
PrivacyPR: A Dataset of Real-World Privacy Fixes for Benchmarking Privacy-Aware Code Review
Coding agents increasingly review code, yet whether they catch the privacy defects that laws such as the GDPR require software to avoid remains largely untested, partly because few datasets connect real privacy defects to their accepted fixes and review context. We present PrivacyPR, a dataset of 4,131 merged GitHub pull requests (PRs) from 1,469 repositories, created between June 2018 and January 2024.
From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
Large language model agents are increasingly expected to negotiate and transact autonomously, yet existing benchmarks rarely combine multimodal product grounding, multi-issue bargaining, and competitive multi-agent markets. We introduce AgenticPay, a unified benchmark for evaluating multimodal agents' ability to reach high-welfare, multidimensional agreements in realistic markets.
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment inadvertently facilitates the transfer of safety vulnerabilities across modalities remains underexplored.
Can LLMs Write Backdoors? An Empirical Security Study of Weight-Space Programming
Recent advances in weight-space programming (WSP) have demonstrated that large language models (LLMs) can directly inspect and modify neural network weights without conventional gradient-based training. While this capability opens new possibilities for model improvement, it also raises an important security question: Can LLMs exploit weight-space programming to inject backdoors into neural networks?
Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable and generalizable execution-grounded environments remain scarce, limiting progress in training more capable ML agents.
REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming
Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it.
HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem.
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and observe that requests resembling normal user queries tend to have higher filter pass rates than those containing obvious anomalous patterns.
