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
Three reasons why AI is not conscious and perhaps never will be
Analogue fast Fourier transforms for scalable and efficient signal processing
New preprints (not yet peer-reviewed)
MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents
MLLM-based mobile agents are rapidly gaining autonomy in perception, planning, and closed-loop execution in dynamic mobile environments. However, this autonomy also broadens the attack surface and amplifies the risks of malicious misuse, including privacy leakage, device compromise, and large-scale phishing.
MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection.
Cryptographically Secure Agent-to-Agent Communication in Multi-Agent Systems
Multi-agent systems (MAS) comprise AI agents that collaborate or compete to perform complex, distributed tasks. Their dynamic interactions create opportunities for threat actors to target and impersonate other agents, intercept messages, inject malicious prompts, and exfiltrate sensitive data while simultaneously complicating the detection of anomalous behavior through conventional monitoring.
Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate (ASR), which treats every failed attack as a successful defense.
Stealthy Poisoning Attacks via Reused KV Cache of Reasoning
Modern large language model (LLM) systems reuse key-value (KV) caches to accelerate inference. Recent work has shown that reusing KV caches from reasoning traces can also improve task performance, similar to retrieval-augmented generation (RAG).
AgentLoupe: Kernel-Resident Semantic Causal Labels for AI Agent Observability
AI agents translate user intents into system actions via tool invocations. Accurately attributing these actions to their originating LLM interactions is essential for security auditing, yet existing methods, such as AgentSight, fail for delayed execution and cross-process-lineage behaviors.
What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics
AI agents increasingly browse the web on users' behalf, yet they consume webpages as screenshots or text, exposing their LLMs to unvetted third-party content. Browsers enforce semantics under which what an element can do depends on what it is and where it comes from, not on what it says.
VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program Structure
Static Application Security Testing (SAST) reports flag operations whose safety depends on project-specific context, and maintainers must decide which reports describe real defects. Large language models (LLMs) can interpret this context, but adjudicating a report with them requires the decisive code, which often lies far from the reported line, and a decision basis that program analysis can check.