Detecting AI Trojans Using Meta Neural Analysis

8 October 2019

Papers citing "Detecting AI Trojans Using Meta Neural Analysis"

50 / 52 papers shown

Title
Cert-SSB: Toward Certified Sample-Specific Backdoor Defense Ting Qiao Y. Wang Xing Liu Sixing Wu Jianbing Li Yiming Li AAML SILM 66 0 0 30 Apr 2025
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation Haiyang Yu Tian Xie Jiaping Gui Pengyang Wang P. Yi Yue Wu 50 1 0 17 Nov 2024
Persistent Backdoor Attacks in Continual Learning Zhen Guo Abhinav Kumar R. Tourani AAML 23 3 0 20 Sep 2024
Model-agnostic clean-label backdoor mitigation in cybersecurity environments Giorgio Severi Simona Boboila J. Holodnak K. Kratkiewicz Rauf Izmailov Alina Oprea Alina Oprea AAML 32 1 0 11 Jul 2024
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection Wei Li Pin-Yu Chen Sijia Liu Ren Wang AAML 43 3 0 09 Jun 2024
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks A. Unnervik Hatef Otroshi-Shahreza Anjith George S´ebastien Marcel AAML SILM 32 0 0 28 Feb 2024
Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models Hongbin Liu Michael K. Reiter Neil Zhenqiang Gong AAML 30 2 0 22 Feb 2024
Comprehensive Assessment of Jailbreak Attacks Against LLMs Junjie Chu Yugeng Liu Ziqing Yang Xinyue Shen Michael Backes Yang Zhang AAML 35 65 0 08 Feb 2024
Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance Wenqi Wei Ling Liu 25 16 0 02 Feb 2024
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks Changjiang Li Ren Pang Bochuan Cao Zhaohan Xi Jinghui Chen Shouling Ji Ting Wang AAML 36 6 0 14 Dec 2023
Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots Ruixiang Tang Jiayi Yuan Yiming Li Zirui Liu Rui Chen Xia Hu AAML 36 13 0 28 Oct 2023
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models Xinyue Shen Z. Chen Michael Backes Yun Shen Yang Zhang SILM 33 244 0 07 Aug 2023
DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation Zhicong Yan Shenghong Li Ruijie Zhao Yuan Tian Yuanyuan Zhao AAML 36 11 0 13 Jun 2023
Poisoning Web-Scale Training Datasets is Practical Nicholas Carlini Matthew Jagielski Christopher A. Choquette-Choo Daniel Paleka Will Pearce Hyrum S. Anderson Andreas Terzis Kurt Thomas Florian Tramèr SILM 31 182 0 20 Feb 2023
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering Rui Zhu Di Tang Siyuan Tang Guanhong Tao Shiqing Ma XiaoFeng Wang Haixu Tang DD 16 3 0 29 Jan 2023
TrojanPuzzle: Covertly Poisoning Code-Suggestion Models H. Aghakhani Wei Dai Andre Manoel Xavier Fernandes Anant Kharkar Christopher Kruegel Giovanni Vigna David E. Evans B. Zorn Robert Sim SILM 21 33 0 06 Jan 2023
Backdoor Attacks Against Dataset Distillation Yugeng Liu Zheng Li Michael Backes Yun Shen Yang Zhang DD 31 27 0 03 Jan 2023
"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice Giovanni Apruzzese Hyrum S. Anderson Savino Dambra D. Freeman Fabio Pierazzi Kevin A. Roundy AAML 31 75 0 29 Dec 2022
XMAM:X-raying Models with A Matrix to Reveal Backdoor Attacks for Federated Learning Jianyi Zhang Fangjiao Zhang Qichao Jin Zhiqiang Wang Xiaodong Lin X. Hei AAML FedML 32 0 0 28 Dec 2022
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks Zeyang Sha Xinlei He Pascal Berrang Mathias Humbert Yang Zhang AAML 13 33 0 18 Dec 2022
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models Rui Zhu Di Tang Siyuan Tang XiaoFeng Wang Haixu Tang AAML FedML 29 13 0 09 Dec 2022
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning Jinghuai Zhang Hongbin Liu Jinyuan Jia Neil Zhenqiang Gong AAML 33 20 0 15 Nov 2022
Dormant Neural Trojans Feisi Fu Panagiota Kiourti Wenchao Li AAML 26 0 0 02 Nov 2022
Training set cleansing of backdoor poisoning by self-supervised representation learning H. Wang Soroush Karami Ousmane Amadou Dia H. Ritter E. Emamjomeh-Zadeh J. Chen Zhen Xiang D. J. Miller G. Kesidis SSL 15 4 0 19 Oct 2022
Universal Backdoor Attacks Detection via Adaptive Adversarial Probe Yuhang Wang Huafeng Shi Rui Min Ruijia Wu Siyuan Liang Yichao Wu Ding Liang Aishan Liu AAML 37 7 0 12 Sep 2022
An Adaptive Black-box Defense against Trojan Attacks (TrojDef) Guanxiong Liu Abdallah Khreishah Fatima Sharadgah Issa M. Khalil AAML 16 8 0 05 Sep 2022
An anomaly detection approach for backdoored neural networks: face recognition as a case study A. Unnervik S´ebastien Marcel AAML 16 4 0 22 Aug 2022
Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy Wenqiang Ruan Ming Xu Wenjing Fang Li Wang Lei Wang Wei Han 32 12 0 18 Aug 2022
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons Mingyuan Fan Yang Liu Cen Chen Ximeng Liu Wenzhong Guo AAML 13 4 0 13 Aug 2022
DECK: Model Hardening for Defending Pervasive Backdoors Guanhong Tao Yingqi Liu Shuyang Cheng Shengwei An Zhuo Zhang Qiuling Xu Guangyu Shen Xiangyu Zhang AAML 18 7 0 18 Jun 2022
Backdoor Defense via Decoupling the Training Process Kunzhe Huang Yiming Li Baoyuan Wu Zhan Qin Kui Ren AAML FedML 19 185 0 05 Feb 2022
Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation Zayd Hammoudeh Daniel Lowd TDI 18 28 0 25 Jan 2022
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World Hua Ma Yinshan Li Yansong Gao A. Abuadbba Zhi-Li Zhang Anmin Fu Hyoungshick Kim S. Al-Sarawi N. Surya Derek Abbott 21 34 0 21 Jan 2022
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios Zhen Xiang David J. Miller G. Kesidis AAML 28 47 0 20 Jan 2022
Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks Xiangyu Qi Tinghao Xie Ruizhe Pan Jifeng Zhu Yong-Liang Yang Kai Bu AAML 25 57 0 25 Nov 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data Yige Li X. Lyu Nodens Koren Lingjuan Lyu Bo-wen Li Xingjun Ma OnRL 6 320 0 22 Oct 2021
Quantization Backdoors to Deep Learning Commercial Frameworks Hua Ma Huming Qiu Yansong Gao Zhi-Li Zhang A. Abuadbba Minhui Xue Anmin Fu Jiliang Zhang S. Al-Sarawi Derek Abbott MQ 30 19 0 20 Aug 2021
TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis Esha Sarkar Michail Maniatakos 24 3 0 14 Aug 2021
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning Jinyuan Jia Yupei Liu Neil Zhenqiang Gong SILM SSL 24 151 0 01 Aug 2021
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers Stefanos Koffas Jing Xu Mauro Conti S. Picek AAML 17 66 0 30 Jul 2021
Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers C. Ashcraft Kiran Karra 15 22 0 14 Jun 2021
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution Fanchao Qi Yuan Yao Sophia Xu Zhiyuan Liu Maosong Sun SILM 22 126 0 11 Jun 2021
A Backdoor Attack against 3D Point Cloud Classifiers Zhen Xiang David J. Miller Siheng Chen Xi Li G. Kesidis 3DPC AAML 28 76 0 12 Apr 2021
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry Yingqi Liu Guangyu Shen Guanhong Tao Zhenting Wang Shiqing Ma X. Zhang AAML 22 8 0 16 Mar 2021
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization Guangyu Shen Yingqi Liu Guanhong Tao Shengwei An Qiuling Xu Shuyang Cheng Shiqing Ma X. Zhang AAML 17 117 0 09 Feb 2021
Baseline Pruning-Based Approach to Trojan Detection in Neural Networks P. Bajcsy Michael Majurski AAML 31 8 0 22 Jan 2021
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification Shuyang Cheng Yingqi Liu Shiqing Ma X. Zhang AAML 15 154 0 21 Dec 2020
TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors Ren Pang Zheng-Wei Zhang Xiangshan Gao Zhaohan Xi S. Ji Peng Cheng Xiapu Luo Ting Wang AAML 27 31 0 16 Dec 2020
DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation Han Qiu Yi Zeng Shangwei Guo Tianwei Zhang Meikang Qiu B. Thuraisingham AAML 16 191 0 13 Dec 2020
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases Ren Wang Gaoyuan Zhang Sijia Liu Pin-Yu Chen Jinjun Xiong Meng Wang AAML 22 148 0 31 Jul 2020