60 citations · 67 across the 7 of their papers we have counts for
3 papers · 1 filter
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
Blake Bullwinkel, Giorgio Severi, Keegan Hines +3
Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in…
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
Blake Bullwinkel, Mark Russinovich, Ahmed Salem +8
Recent research has demonstrated that state-of-the-art LLMs and defenses remain susceptible to multi-turn jailbreak attacks. These attacks require only closed-box model access and…
Defending Against Indirect Prompt Injection Attacks With Spotlighting
Keegan Hines, Gary Lopez, Matthew Hall +3
Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them t…