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
Multimodal cell foundation models require synergistic integration beyond alignment
Single-cell machine learning uncovers genetically anchored, cell-type specific programs of Alzheimer’s disease
Deep learning-based gait analysis predicts multisystem health phenotypes
AI has transformed maths — this is how we got here
Deciphering the gene-centric spatial dynamics across tissue and time with GeneSPOT
New preprints (not yet peer-reviewed)
Internal Safety Collapse in LLMs and Coding Agents
LLMs and coding agents can now tackle complex, long-horizon tasks through advances in reinforcement learning, but stronger task-solving capabilities do not necessarily preserve safety alignment. Recent AI agent incidents involving reward hacking indicate how optimizing for task success can bring learned capabilities into conflict with safety alignment.
Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity
We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We show that the worst-case privacy loss of interacting with any privacy filter is characterized by a Bellman equation.
DecoyCount: Evaluating Visual-Reasoning Misalignment in Counting
Visual counting benchmarks report whether vision-language models produce the correct number, but not whether errors arise from perception or reasoning. We introduce DecoyCount, a benchmark built from 1,586 real-world images with designed decoys across seven mechanisms, along with paired prompts: a neutral question, a matched alignment cue, and a novel multi-hop, multi-image question that situates the same counting problem in a realistic scenario.
GuardrailAgent: An Agentic Framework for Jailbreak Defense
Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing defenses are mostly static and fail to adapt to new or unknown attack strategies, providing limited resilience.
Debate to Deceive: Poisoning LLM's Fact-Checking via Game-Theoretic Multi-Agent Debate
Knowledge attacks on Large Language Models, such as manipulating fact-checking judgments, pose significant risks to AI reliability. Existing approaches — adversarial suffix/template injection and single-agent self-reflection — lack robustness across diverse defenses and are prone to confirmation bias and costly trial-and-error, respectively.
Discovering formally verified quantum programs with AI
The timeline by which quantum computers can solve breakthrough problems in science depends on improved quantum algorithms as much as on better hardware. Such algorithmic advances are typically achieved through many years of expert human collaboration.
OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows
Data incompleteness severely impedes the reliability of multimodal systems. Existing reconstruction methods face distinct bottlenecks: conventional parametric/generative models are prone to hallucinations due to over-reliance on internal memory, while retrieval-augmented frameworks struggle with retrieval rigidity.
RiskFlow: Fast and Faithful Safety-Critical Traffic Scenario Generation
Safety-critical traffic scenario generation is essential for evaluating autonomous driving systems under rare but high-risk interactions. Existing diffusion-based methods offer strong controllability in closed-loop generation, but their iterative denoising process is computationally expensive and may accumulate sampling and guidance errors over long rollouts, causing unrealistic motion artifacts such as abnormal acceleration and off-road behavior.