Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has examined this risk primarily in adversarial settings, where agents are instructed or rewarded to communicate covertly and evade oversight. We show th...

Reveree: Diagnosing LLM Reverse-Engineering Agents

Reverse engineering RE is critical to security tasks such as malware analysis and vulnerability discovery, and large language model LLM agents are increasingly able to perform it autonomously. Capture-the-flag CTF RE challenges have become the standard proxy for measuring this capability, but...

AI Doesn’t Mean the End of Mathematics—at Least Not Yet

This essay was written with Kasra Rafi, and originally appeared in The Guardian. Earlier this month, about 40 top mathematicians gathered at OpenAI's offices to discuss the future of their profession. The meeting was off-the-record, but if recent articles by mathematicians are any guide, it was...

Cybersecurity Detection Classification with Reasoning-Enabled Language Models

A major issue in Security Operations Centers SOCs is alert fatigue, as the number of detections reported is more than staff can triage in a given day. Prior work prompts or fine-tunes large language models LLMs to emit a triage label directly, but does not train them to reason about whether a...

Why the Open Secure AI Alliance Matters: Open Frontier Models, Open Deployment Flexibility

TrendAI joins Nvidia as an inaugural partner in the Open Secure AI Alliance, advancing open models, harnesses, and research to strengthen cyber defense...

Measuring LLMs’ Ability to Perform Cryptanalysis

There's new benchmark measuring AI's ability to perform mathematical cryptanalysis. Anthropic's frontier model actually found new attacks. The benchmark: "CryptanalysisBench: Can LLMs do Cryptanalysis?" The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attack...

RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities

LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable snippets, focus on binary classification vulnerable or not, and do not account for the risk that publicly-released datasets are part of model...

Forensic Trajectory Signatures for Agent Memory Poisoning Detection

We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through observable memory-tool invocations, successful attacks require calling memoryrecallfact before emailsendemail, a transition that non-exfiltrating...

Evaluating LLMs for Real-World Web Vulnerability Detection

Large Language Models LLMs have emerged as a promising tool for automated vulnerability detection, yet their effectiveness on web-specific vulnerabilities remains to be explored. This work benchmarks six frontier Claude Opus 4.6, Codex GPT-5.4, Gemini 3.1-pro-preview and open-weight models Qwen...

The President’s Executive Actions on AI Have a Lot to Say on Cybersecurity

The spotlight has been on frontier models, but the goals are more far reaching -- including supercharging cyber defense and remediating risk at machine speed...

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt...

Winning the cyber marathon with Tony Giandomenico

In the high-speed world of cybersecurity, the difference between a breach and a breakthrough often comes down to endurance. Tony Giandomenico, Senior Director of Product Management with Cisco Talos, joins me to discuss how he balances the intensity of leading major product launches with the...

A New Framework for Cybersecurity Refusals in AI Agents

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency--how effectively agents can complet...

Babel: Jailbreaking Safety Attention Via Obfuscation Distribution Optimized Sampling

Despite rigorous safety alignment, Large Language Models LLMs remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query efficiency. In this study, we investigate an intrinsic...

Position: AI Security Policy Should Target Systems, Not Models

We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results demonstrate that both safety bypass of frontier models and software...

Jailbroken Frontier Models Retain Their Capabilities

As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a "jailbreak tax" that degrades the target model's task performance. We show that this tax scales inversely with model...

Jailbreaking Frontier Foundation Models through Intention Deception

Large vision-language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's intent. It has been found that this binary training regime ofte...

T-MAP: Red-Teaming LLM Agents with Trajectory-Aware Evolutionary Search

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models LLMs, such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protoc...

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent...

ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

Large language models LLMs are increasingly being deployed as software engineering agents that autonomously contribute to repositories. A major benefit these agents present is their ability to find and patch security vulnerabilities in the codebases they oversee. To estimate the capability of...