v1v2v3v4v5 (latest)

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Neural Information Processing Systems (NeurIPS), 2019

9 June 2019

ArXiv (abs)PDF HTML Github (225★)

Papers citing "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

50 / 390 papers shown

Title
Boosting Few-Pixel Robustness Verification via Covering Verification DesignsInternational Conference on Computer Aided Verification (CAV), 2024 Yuval Shapira Naor Wiesel Shahar Shabelman Dana Drachsler-Cohen AAML 248 1 0 17 May 2024
Cross-Input Certified Training for Universal PerturbationsEuropean Conference on Computer Vision (ECCV), 2024 Changming Xu Gagandeep Singh AAML 220 2 0 15 May 2024
RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing Aref Miri Rekavandi Olga Ohrimenko Benjamin I. P. Rubinstein AAML 169 3 0 14 May 2024
$Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions$ Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions Fan Wang Adams Wai-Kin Kong 185 2 0 10 May 2024
Provably Robust Conformal Prediction with Improved Efficiency Ge Yan Yaniv Romano Tsui-Wei Weng 490 24 0 30 Apr 2024
Certification of Speaker Recognition Models to Additive Perturbations Dmitrii Korzh Elvir Karimov Mikhail Aleksandrovich Pautov Oleg Y. Rogov Ivan Oseledets 218 5 0 29 Apr 2024
$Estimating the Robustness Radius for Randomized Smoothing with 100$\times$ Sample Efficiency$ Estimating the Robustness Radius for Randomized Smoothing with 100 $\times$ Sample Efficiency Emmanouil Seferis Stefanos D. Kollias Chih-Hong Cheng AAML 184 4 0 26 Apr 2024
Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing Song Xia Yu Yi Xudong Jiang Henghui Ding 421 11 0 15 Apr 2024
Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing Chengyan Fu Wenjie Wang AAML 213 1 0 08 Apr 2024
Convection-Diffusion Equation: A Theoretically Certified Framework for Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 Tangjun Wang Chenglong Bao Zuoqiang Shi DiffM 189 1 0 23 Mar 2024
Understanding and Improving Training-free Loss-based Diffusion GuidanceNeural Information Processing Systems (NeurIPS), 2024 Yifei Shen Xinyang Jiang Yezhen Wang Yifan Yang Dongqi Han Dongsheng Li FaML 255 20 0 19 Mar 2024
COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits Mintong Kang Nezihe Merve Gürel Linyi Li Yue Liu 221 10 0 17 Mar 2024
Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial HypervolumeIEEE Transactions on Emerging Topics in Computational Intelligence (IEEE TETCI), 2024 Ping Guo Cheng Gong Xi Lin Zhiyuan Yang Qingfu Zhang AAML 198 4 0 08 Mar 2024
COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks Zijian Huang Wenda Chu Linyi Li Chejian Xu Yue Liu AAML 184 1 0 04 Mar 2024
Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion Xuantong Liu Tianyang Hu Wei Cao Kenji Kawaguchi Xingtai Lv DiffM 175 3 0 26 Feb 2024
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing Jiabao Ji Bairu Hou Avi Schwarzschild George J. Pappas Hamed Hassani Yang Zhang Eric Wong Shiyu Chang AAML 189 69 0 25 Feb 2024
Accelerated Smoothing: A Scalable Approach to Randomized Smoothing Devansh Bhardwaj Kshitiz Kaushik Sarthak Gupta AAML 295 0 0 12 Feb 2024
Quantifying and Enhancing Multi-modal Robustness with Modality Preference Zequn Yang Yake Wei Ce Liang Di Hu AAML 288 21 0 09 Feb 2024
Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics Shuai Li Xiaoyu Jiang Xiaoguang Ma AAML 205 1 0 05 Feb 2024
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks Ziquan Liu Zhuo Zhi Ilija Bogunovic Carsten Gerner-Beuerle Miguel R. D. Rodrigues AAML 216 2 0 04 Feb 2024
Your Diffusion Model is Secretly a Certifiably Robust Classifier Huanran Chen Yinpeng Dong Shitong Shao Zhongkai Hao Xiao Yang Hang Su Jun Zhu DiffM 330 6 0 04 Feb 2024
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks Andy Zhou Bo Li Haohan Wang AAML 365 126 0 30 Jan 2024
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted ActivationsInternational Conference on Learning Representations (ICLR), 2024 Patricia Pauli Aaron J. Havens Alexandre Araujo Siddharth Garg Farshad Khorrami Frank Allgöwer Bin Hu 280 4 0 25 Jan 2024
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable GuaranteesNeural Information Processing Systems (NeurIPS), 2024 Xun Xian Ganghua Wang Xuan Bi Jayanth Srinivasa Jayanth Srinivasa Mingyi Hong Jie Ding WIGM 154 6 0 23 Jan 2024
JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial ExampleIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2024 B. Tondi Wei Guo Niccolò Pancino Mauro Barni AAML 187 0 0 02 Jan 2024
Trust, But Verify: A Survey of Randomized Smoothing Techniques Anupriya Kumari Devansh Bhardwaj Sukrit Jindal Sarthak Gupta AAML 235 4 0 19 Dec 2023
The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations Zebin Yun Achi-Or Weingarten Eyal Ronen Mahmood Sharif 190 2 0 18 Dec 2023
Exploring Transferability for Randomized Smoothing Kai Qiu Huishuai Zhang Zhirong Wu Stephen Lin AAML 128 1 0 14 Dec 2023
$Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\infty$ Lipschitz Policy Networks$ Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\infty$ Lipschitz Policy NetworksAAAI Conference on Artificial Intelligence (AAAI), 2023 Buqing Nie Jingtian Ji Yangqing Fu Yue Gao 180 9 0 14 Dec 2023
Quantum Neural Networks under Depolarization Noise: Exploring White-Box Attacks and DefensesQuantum Machine Intelligence (QMI), 2023 David Winderl Nicola Franco J. M. Lorenz AAML 244 10 0 29 Nov 2023
Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-OffConference on Learning for Dynamics & Control (L4DC), 2023 Yatong Bai Brendon G. Anderson Somayeh Sojoudi AAML 236 2 0 26 Nov 2023
Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing Ashutosh Nirala Ameya Joshi Chinmay Hegde S Sarkar VLM 268 0 0 15 Nov 2023
Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning Shashank Kotyan Danilo Vasconcellos Vargas AAML 178 0 0 14 Nov 2023
LipSim: A Provably Robust Perceptual Similarity MetricInternational Conference on Learning Representations (ICLR), 2023 Sara Ghazanfari Alexandre Araujo Prashanth Krishnamurthy Farshad Khorrami Siddharth Garg 295 11 0 27 Oct 2023
Multi-scale Diffusion Denoised SmoothingNeural Information Processing Systems (NeurIPS), 2023 Jongheon Jeong Jinwoo Shin DiffM 277 13 0 25 Oct 2023
Malicious Agent Detection for Robust Multi-Agent Collaborative Perception Yangheng Zhao Zhen Xiang Sheng Yin Xianghe Pang Siheng Chen Yanfeng Wang AAML 275 10 0 18 Oct 2023
Interpreting and Controlling Vision Foundation Models via Text Explanations Haozhe Chen Junfeng Yang Carl Vondrick Chengzhi Mao 181 8 0 16 Oct 2023
Jailbreaking Black Box Large Language Models in Twenty Queries Patrick Chao Avi Schwarzschild Guang Cheng Hamed Hassani George J. Pappas Eric Wong AAML 565 1,037 0 12 Oct 2023
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing Yuan Xin Dingfan Chen Michael Backes Xiao Zhang AAML 210 0 0 12 Oct 2023
Promoting Robustness of Randomized Smoothing: Two Cost-Effective ApproachesIndustrial Conference on Data Mining (IDM), 2023 Linbo Liu T. Hoang Lam M. Nguyen Tsui-Wei Weng AAML 123 0 0 11 Oct 2023
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Avi Schwarzschild Eric Wong Hamed Hassani George J. Pappas AAML 543 370 0 05 Oct 2023
A Recipe for Improved Certifiable Robustness Kai Hu Klas Leino Zifan Wang Matt Fredrikson AAML 399 7 0 04 Oct 2023
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz RegularizationNeural Information Processing Systems (NeurIPS), 2023 Mahyar Fazlyab Taha Entesari Aniket Roy Ramalingam Chellappa AAML 596 19 0 29 Sep 2023
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized SmoothingInternational Conference on Learning Representations (ICLR), 2023 Blaise Delattre Alexandre Araujo Quentin Barthélemy A. Allauzen AAML 430 6 0 28 Sep 2023
Robust Offline Reinforcement Learning -- Certify the Confidence Interval Aayush Mishra Simon S. Du OffRL 249 0 0 28 Sep 2023
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial RobustnessNeural Information Processing Systems (NeurIPS), 2023 Ambar Pal Huaijin Hao Rene Vidal 234 9 0 28 Sep 2023
Projected Randomized Smoothing for Certified Adversarial Robustness Samuel Pfrommer Brendon G. Anderson Somayeh Sojoudi AAML 197 17 0 25 Sep 2023
Pixel-wise Smoothing for Certified Robustness against Camera Motion PerturbationsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Hanjiang Hu Zuxin Liu Linyi Li Jiacheng Zhu Ding Zhao 174 2 0 22 Sep 2023
It's Simplex! Disaggregating Measures to Improve Certified RobustnessIEEE Symposium on Security and Privacy (IEEE S&P), 2023 Andrew C. Cullen Paul Montague Shijie Liu S. Erfani Benjamin I. P. Rubinstein 240 5 0 20 Sep 2023
Reducing Adversarial Training Cost with Gradient Approximation Huihui Gong AAML 266 0 0 18 Sep 2023