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
Machine learning dataset and benchmark for accurate T cell receptor–pHLA binding prediction
Development of an automated method for audiometric data extraction and analysis using voting optical character recognition
Emergence of diffusion models from associative memory through memorization and generalization
New preprints (not yet peer-reviewed)
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly vulnerable to prompt injection attacks, where adversarial instructions embedded in HTML or rendered screenshots can manipulate agent behavior and lead to harmful outcomes such as information leakage.
Do AI-for-Science Agents Preserve Model Safety?
AI-for-Science agents are increasingly being used for formulating scientific hypotheses, running autonomous experiments, and interpreting evidence. These agents are constructed by integrating a large language model (LLM) into a domain-specific agent harness, which in turn can improve the LLM's scientific capability and enable the model to orchestrate scientific tools.
Quantum Cadence: Post-Quantum Consensus with Multiple Concurrent Proposers
The consensus protocols of most high-performance blockchains use quorum certificates, which bundle the signatures of a quorum of validators. Signature schemes such as BLS can aggregate the signatures of a whole quorum into a single short signature, which keeps these certificates small.
Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability
Advances in Omni-modal Large Language Models (OLLMs) have enabled increasingly seamless human-AI interaction, but their unified processing of heterogeneous modalities also expands the attack surface, allowing adversaries to exploit richer input compositions to circumvent safety alignment. To counter such risks, omni-modal guardrails have been proposed to detect and filter unsafe queries across arbitrary modalities.
Knowing Whom to Trust is not Enough: The Trust–Agreement Gap in Repeated Multi-Party LLM Negotiation
Large language model (LLM) agents increasingly participate in negotiations on behalf of individuals and organizations, yet they remain vulnerable to manipulation, particularly in repeated multi-party interactions. Classical multi-agent systems address this challenge through explicit trust and reputation models, whereas existing work on LLM negotiation largely treats trust as an emergent phenomenon.
The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows
LLM agents are increasingly deployed in collaborative settings where they pursue separate tasks while sharing resources and operating under review or oversight processes. Such settings create safety risks not only when agents are malicious, but also when they are simply trying to help.
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models
Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated use of shared parameters across recurrent steps. Since each recurrent depth can be read out independently, a single LoopLM exposes a broader output space across inference depths, raising an important question: whether safety is preserved throughout recurrent computation.
On Task, Off Track: Benchmarking LLM and Agent Robustness to Near-Target Prompt Injection
Prompt injection benchmarks assess whether large language models (LLMs) and agents resist malicious instructions embedded in external content. However, a system could perform well by rejecting attacks that obviously abandon the user's request, while still accepting changes that retain most of a legitimate answer but make it incorrect or harmful.