ORBIT: A Framework for Multi-Agent Safety and Security Evaluations

Multi-agent LLM systems are increasingly deployed for complex, long-horizon tasks or emerge as a natural consequence of agents interacting in the wild. Yet they give rise to significant safety and security risks: the flexible protocols that enable task generalization also expose novel threats, fr...

Black Hat USA 2024 Conference Slides

Black Hat USA 2024 conference slides for topics Self-Hosted GitHub CI/CD Runners: Continuous Integration, Continuous Destruction, From Weapon to Target: Quantum Computers Paradox, Listen Up: Sonos Over-The-Air Remote Kernel Exploitation and Covert Wiretap, Windows Downdate: Downgrade Attacks Usin...

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-Offs

Jailbreak defenses are essential for protecting large language models LLMs, but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cos...

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be...

AI-Accelerated Brute Force Cryptanalysis

Modern cryptography is hinged on "not learning from mistakes": trying numerous wrong keys, should not help one identify the right key. Indeed, it worked -- until recently when the surprising power of AI to see pattern in apparent randomness has turned the 'wrong plaintexts' generated by the 'wron...

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw As a Case Study

Autonomous agent frameworks built upon large language models LLMs are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and...

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models

Large language models LLMs are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn InjectionTTI, a new multi-turn attack technique that systematically exploits stateless moderation by distributing...

Your Agent Is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt...

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats

Autonomous Large Language Model LLM agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege execution capabilities substantially expand the system attack...

Cybersecurity AI: Hacking Consumer Robots in the AI Era

Is robot cybersecurity broken by AI? Consumer robots -- from autonomous lawnmowers to powered exoskeletons and window cleaners -- are rapidly entering homes and workplaces, yet their security remains rooted in assumptions of specialized attacker expertise. This paper presents evidence that...

Backdoor Attacks on Contrastive Continual Learning for IoT Systems

The Internet of Things IoT systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift, changing user behavior, device aging, and adversarial dynamics. Contrastive continual learning CCL combines contrastiv...

Hardware-Triggered Backdoors

Machine learning models are routinely deployed on a wide range of computing hardware. Although such hardware is typically expected to produce identical results, differences in its design can lead to small numerical variations during inference. In this work, we show that these variations can be...

Why AI Keeps Falling for Prompt Injection Attacks

Imagine you work at a drive-through restaurant. Someone drives up and says: "I'll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer." Would you hand over the money? Of course not. Yet this is what large language models LLMs do...

Techniques of Modern Attacks

The techniques used in modern attacks have become an important factor for investigation. As we advance further into the digital age, cyber attackers are employing increasingly sophisticated and highly threatening methods. These attacks target not only organizations and governments but also extend...

7 Reasons to Get Certified in API Security

API security is becoming more important by the day and skilled practitioners are in high demand. Now’s the time to level up your API security skillset. Wallarm University, our free training course, provides security analysts, engineers, and practitioners with hands-on skills you can’t get from...

Cybersecurity in the Public Sector: Challenges, Strategies and Best Practices

Public sector cybersecurity faces outdated systems, budget gaps, and rising attacks. Learn key challenges, defense strategies, and proven best practices...

Jailbreaking LLMs and VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models LLMs and Vision-Language Models VLMs, emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It...

Link11 Identifies Five Cybersecurity Trends Set to Shape European Defense Strategies in 2026

Frankfurt am Main, Germany, 16th December 2025, CyberNewsWire...

Account Takeover: What Is It and How to Fight It

Account takeover ATO attacks can devastate individuals and organisations, from personal profiles to enterprise systems. The financial impact…...

Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems

Extended reality XR applications increasingly integrate Large Language Models LLMs to enhance user experience, scene understanding, and even generate executable XR content, and are often called "AI glasses". Despite these potential benefits, the integrated XR-LLM pipeline makes XR applications...