collaborators

8 papers

cs.CR2026

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs

Rui Wen, Mark Russinovich, Andrew Paverd +2

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical appli…

cs.CL2026

Highlight & Summarize: RAG without the jailbreaks

Giovanni Cherubin, Andrew Paverd

Preventing jailbreaking and model hijacking of Large Language Models (LLMs) is an important yet challenging task. When interacting with a chatbot, malicious users can input special…

cs.LG2026

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Ahmed Salem, Andrew Paverd, Sahar Abdelnabi

Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is explicitly stored and re-supplied. We ch…

cs.LG2026

Permissive Information-Flow Analysis for Large Language Models

Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf +7

Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from on…

cs.CR2025

Securing AI Agents with Information-Flow Control

Manuel Costa, Boris Köpf, Aashish Kolluri +6

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of i…

cs.LG2025

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…