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
Visual LLM-guided consensus spatial domain detection with L-STAR
RobPicker: a meta-learning framework for robust identification of macromolecules in cryo-electron tomograms
New preprints (not yet peer-reviewed)
BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery
Large Reasoning Models (LRMs) achieve strong performance on complex tasks by generating explicit Chain-of-Thought (CoT) reasoning, but the safety implications of this intermediate reasoning surface remain underexplored. We demonstrate that the reasoning trace itself is a powerful attack vector.
The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service operations directly without navigating websites. This shift changes how existing Web vulnerabilities can be exploited.
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity.
Cyber-JEV: Matched Contrastive Fine-Tuning of Language Models for Fast Source-Code Vulnerability Triage
Single-pass scoring models such as Jev give each code function a vulnerability probability, so that security teams can rank many functions for review without generating written explanations. Training an open-weight model for this task is limited by data.
Measuring Model-Specific Alignment Drift in LLM-Based Opinion Dynamics
Large language model (LLM) agents are increasingly used as synthetic participants in opinion-dynamics experiments, often assuming that an agent's behaviour is fully determined by its prompt. We test this assumption with a framework in which LLM agents discuss a contested policy issue over repeated rounds while their stance is quantified by a fixed psychometric instrument independent of any dynamics model.
The Devil is in the Context: Nine Dimensions of Prompt Injection Attacks
Prompt injection is usually discussed and evaluated as a single, homogeneous type of attack. However, vulnerabilities reported in real-world systems show that prompt injections vary widely.
MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
Optimization modeling translates real decision-making problems into mathematical optimization models and solver-executable implementations. Although language models are increasingly used to generate optimization formulations and solver code, existing benchmarks for this capability are almost entirely text-only.
The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
Large Language Models (LLMs) have shown promise for empowering search agents to tackle complex information-seeking tasks. However, since acquiring external information necessitates web search, these agents are highly susceptible to various adversarial attacks (e.g., malicious information injection or stealthy context manipulation).