2023-04-24-schwinn23a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats	Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense approaches due to faulty defense evaluations. Flawed robustness evaluations necessitate rectifications in subsequent works, dangerously slowing down the research and providing a false sense of security. In this context, we will face substantial challenges associated with an impending adversarial arms race in natural language processing, specifically with closed-source Large Language Models (LLMs), such as ChatGPT, Google Bard, or Anthropic’s Claude. We provide a first set of prerequisites to improve the robustness assessment of new approaches and reduce the amount of faulty evaluations. Additionally, we identify embedding space attacks on LLMs as another viable threat model for the purposes of generating malicious content in open-sourced models. Finally, we demonstrate on a recently proposed defense that, without LLM-specific best practices in place, it is easy to overestimate the robustness of a new approach.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	schwinn23a	0	Adversarial Attacks and Defenses in Large Language Models: Old and New Threats	103	117	103-117	103	false	Schwinn, Leo and Dobre, David and G{\"u}nnemann, Stephan and Gidel, Gauthier	given family Leo Schwinn given family David Dobre given family Stephan Günnemann given family Gauthier Gidel	2023-04-24		Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops	239	inproceedings	date-parts 2023 4 24	https://proceedings.mlr.press/v239/schwinn23a/schwinn23a.pdf