4 papers · 1 filter
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…
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…
LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22
Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous def…
Get my drift? Catching LLM Task Drift with Activation Deltas
Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin +3
LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer q…