AgentWatcher: A Rule-Based Prompt Injection Monitor

Large language models LLMs and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: 1 their effectiveness degrades significantly as context length increases, and 2 they lack...

PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models LLMs convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide...

Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection

Large Language Models LLMs have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or function-level classification, failing to reflect the complexity of...

Jailbreaking in the Haystack

Recent advances in long-context language models LMs have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use agents. Yet, the safety implications of these extended contexts remain unclear. To bridge this gap, we introduce NINJA short for...

SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence

Effective analysis of cybersecurity and threat intelligence data demands language models that can interpret specialized terminology, complex document structures, and the interdependence of natural language and source code. Encoder-only transformer architectures provide efficient and robust...

TracLLM: a Generic Framework for Attributing Long Context LLMs

Long context large language models LLMs are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long context e.g., documents, PDF files, webpages, a long context LLM can generate an output grounded in the provided context,...

What Really Matters in Many-Shot Attacks? an Empirical Study of Long-Context Vulnerabilities in LLMs

We investigate long-context vulnerabilities in Large Language Models LLMs through Many-Shot Jailbreaking MSJ. Our experiments utilize context length of up to 128K tokens. Through comprehensive analysis with various many-shot attack settings with different instruction styles, shot density, topic,...