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
Large language models discover complementary heuristics for combinatorial optimization
Sign of the times: AI lingo muscles into esteemed dictionary
Sign of the times: AI lingo muscles into esteemed dictionary
New preprints (not yet peer-reviewed)
From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model
Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A task sent by a remote peer over A2A is treated as a legitimate request, providing a natural channel for indirect prompt injection.
HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines
Large language model (LLM)-based techniques have achieved notable progress in generating harnesses for program fuzzing. However, applying them to arbitrary functions (especially internal functions) textit{at scale} remains challenging due to the requirement of sophisticated contextual information, such as specification, dependencies, and usage examples.
SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses
Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and efficient solution. The core challenge is twofold: a reproducer must first recover the trigger scaffold needed to reach the vulnerable state and determine the precise concrete values that actually trigger the bug.
No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents
Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning (RL) and large language models (LLMs) offer complementary mechanisms for the planning and execution such agents require, and prior work has combined them in hybrid hierarchies.
A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined
Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and justify a patient's problem representation and a defensible plan.
Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents
Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial comprehension through an architecture combining geometrical tools with a LLM serving as a high-level orchestrator in grid-world environments.
UnifiedAttack: Evaluating the Safety of Large Multimodal Models in Synergistic Harmful Image-Text Generation
As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generation tasks becomes a critical challenge. Unlike unimodal threats, synergistic risks emerge when text and image modalities are coordinated to produce harm that significantly exceeds their individual components.
Safety of Latent Communication in Multi-Agent Systems
Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-based communication. To this end, lightweight trainable links are introduced to map the sender's representations into the receiver's input space.