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
High-risk antimicrobial resistance genomic traits in multidrug-resistant Salmonella across China’s food chain: projections to 2050
Reusability report: multi-sample omics network inference operates in distinct robustness regimes defined by prior knowledge and data availability
Audio long read: How to stay smart in the age of AI — the science of critical thinking
New preprints (not yet peer-reviewed)
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions over failure. However, existing safety benchmarks primarily evaluate whether agents comply with explicitly harmful instructions, leaving the conditions that cause agents to choose harmful actions poorly understood.
CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets.
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents, whether dormant poisoning extends to harmful agent actions and multimodal settings remains unclear.
AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories
LLM agents are increasingly taking actions with real consequences, yet safety evaluations often reduce their behavior to a final safe/unsafe outcome, obscuring whether the agent recognized the risk and how it responded. We introduce AURA-Eval, a framework for evaluating whether agents recognize contextual risk and adapt their behavior accordingly.
Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under a finite budget. We show that autonomous vulnerability discovery exhibits a hypothesis-verification asymmetry, where verifying a candidate hypothesis through reachability analysis, execution, and proof-of-concept construction is substantially more expensive than forming it.
Generative to Agentic AI: Survey, Conceptualization, and Challenges
Agentic AI builds upon Generative AI (GenAI). It constitutes the next major step in the evolution of AI with much stronger reasoning, learning, and interaction capabilities that enable more autonomous behavior to tackle complex, long-running tasks.
Sequential Behavioral Watermarking for LLM Agents
LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership, and unauthorized reuse difficult to establish from observed behavior alone. This motivates watermarking signals embedded directly into agent behavior rather than only into generated text, since text watermarking cannot capture the action-level decisions that define agent execution.
How To Track Qubits Through Space and Time (Or: Sailing in a Quantum Boat)
While quantum position verification aims to certify a prover's location using quantum information, existing security definitions only guarantee that part of the successful adversarial party is in the claimed location. This leaves open the possibility that a distributed team of adversaries can jointly simulate a prover in a way that defeats the intended meaning of `being at a location' in position-based cryptography.