activity
20232026
most citedSecAlign: Defending Against Prompt Injection with Preference Optimization

17 citations · 17 across the 8 of their papers we have counts for

collaborators
Showing cs.CRShow all

8 papers · 1 filter

cs.CR2026

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Sizhe Chen, Yu-Lin Tsai, Ivan Evtimov +4

Prompt injection is widely recognized as a major security threat to AI agents that interact with untrusted external data, such as websites, documents, and emails. Prior work has sh…

cs.CR2026

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Yibo Peng, Long Lian, David Wagner +1

Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject a prompt into the data, sayi…

cs.CR2025

Defending Against Prompt Injection with DataFilter

Yizhu Wang, Sizhe Chen, Raghad Alkhudair +2

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security thr…

cs.CR2025

Defending Against Prompt Injection With a Few DefensiveTokens

Sizhe Chen, Yizhu Wang, Nicholas Carlini +2

When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting inst…

cs.CR2025

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks

Sizhe Chen, Arman Zharmagambetov, David Wagner +1

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Mod…

cs.CR2024

SecAlign: Defending Against Prompt Injection with Preference Optimization

Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar +3

Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advance…