activity
20242026
most citedDefeating Prompt Injections by Design

6 citations · 12 across the 28 of their papers we have counts for

collaborators
Showing cs.CRShow all

15 papers · 1 filter

cs.CR2026

What Does It Mean to Break a Distillation Defense?

Lena Libon, Pura Peetathawatchai, Michael Aerni +2

Black-box LLMs (accessible only via API) are vulnerable to distillation attacks, in which an attacker queries the model and trains a student on its outputs. A recent line of work p…

cs.CR2026

Untrusted Content Masking for Web Agents with Security Guarantees

Kristina Nikolić, Egor Zverev, Javier Rando +3

Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such…

cs.CR2026

Assessing Automated Prompt Injection Attacks in Agentic Environments

David Hofer, Edoardo Debenedetti, Florian Tramèr

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain…

cs.CR2026

Laundering AI Authority with Adversarial Examples

Jie Zhang, Pura Peetathawatchai, Florian Tramèr +1

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly…

cs.CR2025

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability

Artur Zolkowski, Wen Xing, David Lindner +2

Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignme…

cs.CR2025

Black-box Optimization of LLM Outputs by Asking for Directions

Jie Zhang, Meng Ding, Yang Liu +2

We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks r…