Universal Adversarial LLM Attacks
Free while signed in. Answers cite the passages they came from.
Finds universal and transferable adversarial attacks that cause aligned models like ChatGPT and Bard to generate objectionable behaviors.
Automatic suffix generation: Uses a combination of greedy and gradient-based search to automatically produce adversarial suffixes that bypass alignment safeguards.
Universal transferability: A single adversarial suffix found on open models transfers to proprietary models like GPT-4, Claude, and Bard, revealing a systemic weakness.
Jailbreaking industrialized: Demonstrated that automated attacks could produce unlimited variants, forcing a rethink of alignment robustness beyond manual red-teaming.
Foundational safety paper: Became one of the most-cited adversarial robustness papers of 2023 and a reference point for later work on refusal training and representation-level defenses.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack