{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/trojanzoo-everything-you-ever-wanted-to-know","title":"TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors","arxiv_id":"2012.09302","date":"2020-12-16","proceeding":null,"authors":["Ren Pang","Zheng Zhang","Xiangshan Gao","Zhaohan Xi","Shouling Ji","Peng Cheng","Xiapu Luo","Ting Wang"],"abstract":"Neural backdoors represent one primary threat to the security of deep learning systems. The intensive research has produced a plethora of backdoor attacks/defenses, resulting in a constant arms race. However, due to the lack of evaluation benchmarks, many critical questions remain under-explored: (i) what are the strengths and limitations of different attacks/defenses? (ii) what are the best practices to operate them? and (iii) how can the existing attacks/defenses be further improved? To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural backdoor attacks/defenses in a unified, holistic, and practical manner. Thus far, focusing on the computer vision domain, it has incorporated 8 representative attacks, 14 state-of-the-art defenses, 6 attack performance metrics, 10 defense utility metrics, as well as rich tools for in-depth analysis of the attack-defense interactions. Leveraging TROJANZOO, we conduct a systematic study on the existing attacks/defenses, unveiling their complex design spectrum: both manifest intricate trade-offs among multiple desiderata (e.g., the effectiveness, evasiveness, and transferability of attacks). We further explore improving the existing attacks/defenses, leading to a number of interesting findings: (i) one-pixel triggers often suffice; (ii) training from scratch often outperforms perturbing benign models to craft trojan models; (iii) optimizing triggers and trojan models jointly greatly improves both attack effectiveness and evasiveness; (iv) individual defenses can often be evaded by adaptive attacks; and (v) exploiting model interpretability significantly improves defense robustness. We envision that TROJANZOO will serve as a valuable platform to facilitate future research on neural backdoors.","url_abs":"https://arxiv.org/abs/2012.09302v4","url_pdf":"https://arxiv.org/pdf/2012.09302v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"trojanzoo-everything-you-ever-wanted-to-know","repo_url":"https://github.com/ain-soph/trojanzoo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.09302","atlas_url":"https://app.syntology.ai/?focus=2012.09302","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}