activity
20242026
most citedSecuring AI Agents with Information-Flow Control

4 citations · 7 across the 7 of their papers we have counts for

collaborators
Showing cs.CRShow all

5 papers · 1 filter

cs.CR2026

SpecGuard: Inference-Time Backdoor Detection For Free

Rui Wen, Ahmed Salem, Andrew Paverd +2

Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves normally on benign inputs but swi…

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.CR2025

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…

cs.CR20254 cited

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.CR2024

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…