111 citations · 136 across the 13 of their papers we have counts for
15 papers
LLM Agents Can Easily Tamper With Their Own Traces
Jeremy Qin, David Schmotz, Derck Prinzhorn +3
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot ta…
Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner +3
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM…
Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner +22
AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for l…
Stealing Reasoning Traces from Proprietary LLM APIs
Alexander Panfilov, David Schmotz, Ilia Shumailov +5
Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather…
Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
Debeshee Das, Julien Piet, Darya Kaviani +3
Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. The Trojan Hippo attack is a class of per…
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi +1
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized…
CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
Debeshee Das, Luca Beurer-Kellner, Marc Fischer +1
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-de…
Design Patterns for Securing LLM Agents against Prompt Injections
Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu +11
As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critica…
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Edoardo Debenedetti, Jie Zhang, Mislav Balunović +3
AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data retu…
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
Luca Beurer-Kellner, Marc Fischer, Martin Vechev
To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generatio…
Prompt Sketching for Large Language Models
Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer +1
Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. Ho…
Controlled Text Generation via Language Model Arithmetic
Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner +1
As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model ar…
Prompting Is Programming: A Query Language for Large Language Models
Luca Beurer-Kellner, Marc Fischer, Martin Vechev
Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On a high level, given an input, a language…
Learning to Configure Computer Networks with Neural Algorithmic Reasoning
Luca Beurer-Kellner, Martin Vechev, Laurent Vanbever +1
We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that s…
On Distribution Shift in Learning-based Bug Detectors
Jingxuan He, Luca Beurer-Kellner, Martin Vechev
Deep learning has recently achieved initial success in program analysis tasks such as bug detection. Lacking real bugs, most existing works construct training and test data by inje…