default search action
Somesh Jha
Person information
- affiliation: University of Wisconsin-Madison, Madison, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j42]Samarjit Chakraborty, Somesh Jha, Soheil Samii, Philipp Mundhenk:
Introduction to the Special Issue on Automotive CPS Safety & Security: Part 2. ACM Trans. Cyber Phys. Syst. 8(2): 10 (2024) - [j41]Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Ö. Arik, Somesh Jha, Tomas Pfister:
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction. Trans. Mach. Learn. Res. 2024 (2024) - [c193]Neal Mangaokar, Ashish Hooda, Jihye Choi, Shreyas Chandrashekaran, Kassem Fawaz, Somesh Jha, Atul Prakash:
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails. ACL (1) 2024: 10960-10976 - [c192]Zi Wang, Bin Hu, Aaron J. Havens, Alexandre Araujo, Yang Zheng, Yudong Chen, Somesh Jha:
On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks. ICLR 2024 - [c191]Ashish Hooda, Mihai Christodorescu, Miltiadis Allamanis, Aaron Wilson, Kassem Fawaz, Somesh Jha:
Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates. ICML 2024 - [c190]Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha:
Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection. ICML 2024 - [c189]Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash:
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles. WACV 2024: 3800-3810 - [i110]Ashish Hooda, Mihai Christodorescu, Miltiadis Allamanis, Aaron Wilson, Kassem Fawaz, Somesh Jha:
Do Large Code Models Understand Programming Concepts? A Black-box Approach. CoRR abs/2402.05980 (2024) - [i109]Neal Mangaokar, Ashish Hooda, Jihye Choi, Shreyas Chandrashekaran, Kassem Fawaz, Somesh Jha, Atul Prakash:
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails. CoRR abs/2402.15911 (2024) - [i108]Fangzhou Wu, Ning Zhang, Somesh Jha, Patrick D. McDaniel, Chaowei Xiao:
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems. CoRR abs/2402.18649 (2024) - [i107]Mihai Christodorescu, Ryan Craven, Soheil Feizi, Neil Gong, Mia Hoffmann, Somesh Jha, Zhengyuan Jiang, Mehrdad Saberi Kamarposhti, John C. Mitchell, Jessica Newman, Emelia Probasco, Yanjun Qi, Khawaja Shams, Matthew Turek:
Securing the Future of GenAI: Policy and Technology. CoRR abs/2407.12999 (2024) - [i106]Nils Palumbo, Ravi Mangal, Zifan Wang, Saranya Vijayakumar, Corina S. Pasareanu, Somesh Jha:
Mechanistically Interpreting a Transformer-based 2-SAT Solver: An Axiomatic Approach. CoRR abs/2407.13594 (2024) - [i105]Jihye Choi, Nils Palumbo, Prasad Chalasani, Matthew M. Engelhard, Somesh Jha, Anivarya Kumar, David Page:
MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance. CoRR abs/2408.01869 (2024) - [i104]Ashish Hooda, Rishabh Khandelwal, Prasad Chalasani, Kassem Fawaz, Somesh Jha:
PolicyLR: A Logic Representation For Privacy Policies. CoRR abs/2408.14830 (2024) - [i103]Zi Wang, Divyam Anshumaan, Ashish Hooda, Yudong Chen, Somesh Jha:
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks. CoRR abs/2410.04234 (2024) - [i102]Xiaogeng Liu, Peiran Li, Edward Suh, Yevgeniy Vorobeychik, Zhuoqing Mao, Somesh Jha, Patrick McDaniel, Huan Sun, Bo Li, Chaowei Xiao:
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs. CoRR abs/2410.05295 (2024) - [i101]Mihai Christodorescu, Ryan Craven, Soheil Feizi, Neil Zhenqiang Gong, Mia Hoffmann, Somesh Jha, Zhengyuan Jiang, Mehrdad Saberi Kamarposhti, John C. Mitchell, Jessica Newman, Emelia Probasco, Yanjun Qi, Khawaja Shams, Matthew Turek:
Securing the Future of GenAI: Policy and Technology. IACR Cryptol. ePrint Arch. 2024: 855 (2024) - 2023
- [j40]Clark W. Barrett, Brad Boyd, Elie Bursztein, Nicholas Carlini, Brad Chen, Jihye Choi, Amrita Roy Chowdhury, Mihai Christodorescu, Anupam Datta, Soheil Feizi, Kathleen Fisher, Tatsunori Hashimoto, Dan Hendrycks, Somesh Jha, Daniel Kang, Florian Kerschbaum, Eric Mitchell, John C. Mitchell, Zulfikar Ramzan, Khawaja Shams, Dawn Song, Ankur Taly, Diyi Yang:
Identifying and Mitigating the Security Risks of Generative AI. Found. Trends Priv. Secur. 6(1): 1-52 (2023) - [j39]Adam Dziedzic, Christopher A. Choquette-Choo, Natalie Dullerud, Vinith M. Suriyakumar, Ali Shahin Shamsabadi, Muhammad Ahmad Kaleem, Somesh Jha, Nicolas Papernot, Xiao Wang:
Private Multi-Winner Voting for Machine Learning. Proc. Priv. Enhancing Technol. 2023(1): 527-555 (2023) - [j38]Samarjit Chakraborty, Somesh Jha, Soheil Samii, Philipp Mundhenk:
Introduction to the Special Issue on Automotive CPS Safety & Security: Part 1. ACM Trans. Cyber Phys. Syst. 7(1): 1:1-1:6 (2023) - [j37]Mohannad Alhanahnah, Shiqing Ma, Ashish Gehani, Gabriela F. Ciocarlie, Vinod Yegneswaran, Somesh Jha, Xiangyu Zhang:
autoMPI: Automated Multiple Perspective Attack Investigation With Semantics Aware Execution Partitioning. IEEE Trans. Software Eng. 49(4): 2761-2775 (2023) - [c188]Joann Qiongna Chen, Tianhao Wang, Zhikun Zhang, Yang Zhang, Somesh Jha, Zhou Li:
Differentially Private Resource Allocation. ACSAC 2023: 772-786 - [c187]Ryan Feng, Ashish Hooda, Neal Mangaokar, Kassem Fawaz, Somesh Jha, Atul Prakash:
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks. CCS 2023: 786-800 - [c186]Sanjam Garg, Aarushi Goel, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Guru-Vamsi Policharla, Mingyuan Wang:
Experimenting with Zero-Knowledge Proofs of Training. CCS 2023: 1880-1894 - [c185]Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Ö. Arik, Tomas Pfister, Somesh Jha:
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs. EMNLP (Findings) 2023: 5190-5213 - [c184]Jayaram Raghuram, Yijing Zeng, Dolores García, Rafael Ruiz, Somesh Jha, Joerg Widmer, Suman Banerjee:
Few-Shot Domain Adaptation For End-to-End Communication. ICLR 2023 - [c183]Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha:
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning. ICLR 2023 - [c182]Jiefeng Chen, Jayaram Raghuram, Jihye Choi, Xi Wu, Yingyu Liang, Somesh Jha:
Stratified Adversarial Robustness with Rejection. ICML 2023: 4867-4894 - [c181]Jihye Choi, Jayaram Raghuram, Ryan Feng, Jiefeng Chen, Somesh Jha, Atul Prakash:
Concept-based Explanations for Out-of-Distribution Detectors. ICML 2023: 5817-5837 - [c180]Nicholas Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser, Congyu Fang, Somesh Jha, Nicolas Papernot, Xiao Wang:
Robust and Actively Secure Serverless Collaborative Learning. NeurIPS 2023 - [c179]Zifan Wang, Saranya Vijayakumar, Kaiji Lu, Vijay Ganesh, Somesh Jha, Matt Fredrikson:
Grounding Neural Inference with Satisfiability Modulo Theories. NeurIPS 2023 - [c178]Washington Garcia, Pin-Yu Chen, Hamilton Scott Clouse, Somesh Jha, Kevin R. B. Butler:
Less is More: Dimension Reduction Finds On-Manifold Adversarial Examples in Hard-Label Attacks. SaTML 2023: 254-270 - [c177]Zhichuang Sun, Ruimin Sun, Changming Liu, Amrita Roy Chowdhury, Long Lu, Somesh Jha:
ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks. SP 2023: 1596-1612 - [c176]Harrison Rosenberg, Brian Tang, Kassem Fawaz, Somesh Jha:
Fairness Properties of Face Recognition and Obfuscation Systems. USENIX Security Symposium 2023: 7231-7248 - [i100]Matt Fredrikson, Kaiji Lu, Saranya Vijayakumar, Somesh Jha, Vijay Ganesh, Zifan Wang:
Learning Modulo Theories. CoRR abs/2301.11435 (2023) - [i99]Xi Wu, Joe Benassi, Yaqi Zhang, Uyeong Jang, James Foster, Stella Kim, Yujing Sun, Somesh Jha, John Cieslewicz, Jeffrey F. Naughton:
Holistic Cube Analysis: A Query Framework for Data Insights. CoRR abs/2302.00120 (2023) - [i98]Somesh Jha, Mihai Christodorescu, Anh Pham:
Formal Analysis of the API Proxy Problem. CoRR abs/2302.13525 (2023) - [i97]Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha:
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning. CoRR abs/2303.00106 (2023) - [i96]Ryan Feng, Ashish Hooda, Neal Mangaokar, Kassem Fawaz, Somesh Jha, Atul Prakash:
Investigating Stateful Defenses Against Black-Box Adversarial Examples. CoRR abs/2303.06280 (2023) - [i95]Zi Wang, Somesh Jha, Krishnamurthy Dvijotham:
Efficient Symbolic Reasoning for Neural-Network Verification. CoRR abs/2303.13588 (2023) - [i94]Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Ö. Arik, Somesh Jha, Tomas Pfister:
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction. CoRR abs/2304.03870 (2023) - [i93]Jiefeng Chen, Jayaram Raghuram, Jihye Choi, Xi Wu, Yingyu Liang, Somesh Jha:
Stratified Adversarial Robustness with Rejection. CoRR abs/2305.01139 (2023) - [i92]Zi Wang, Jihye Choi, Somesh Jha:
Rethink Diversity in Deep Learning Testing. CoRR abs/2305.15698 (2023) - [i91]Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha:
Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection. CoRR abs/2305.17528 (2023) - [i90]Debopam Sanyal, Jui-Tse Hung, Manav Agrawal, Prahlad Jasti, Shahab Nikkhoo, Somesh Jha, Tianhao Wang, Sibin Mohan, Alexey Tumanov:
Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems. CoRR abs/2307.01292 (2023) - [i89]Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash:
Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks. CoRR abs/2307.16331 (2023) - [i88]Clark W. Barrett, Brad Boyd, Ellie Burzstein, Nicholas Carlini, Brad Chen, Jihye Choi, Amrita Roy Chowdhury, Mihai Christodorescu, Anupam Datta, Soheil Feizi, Kathleen Fisher, Tatsunori Hashimoto, Dan Hendrycks, Somesh Jha, Daniel Kang, Florian Kerschbaum, Eric Mitchell, John C. Mitchell, Zulfikar Ramzan, Khawaja Shams, Dawn Song, Ankur Taly, Diyi Yang:
Identifying and Mitigating the Security Risks of Generative AI. CoRR abs/2308.14840 (2023) - [i87]Mohannad Alhanahnah, Philipp Dominik Schubert, Thomas W. Reps, Somesh Jha, Eric Bodden:
slash: A Technique for Static Configuration-Logic Identification. CoRR abs/2310.06758 (2023) - [i86]Jihye Choi, Shruti Tople, Varun Chandrasekaran, Somesh Jha:
Why Train More? Effective and Efficient Membership Inference via Memorization. CoRR abs/2310.08015 (2023) - [i85]Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Ö. Arik, Tomas Pfister, Somesh Jha:
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs. CoRR abs/2310.11689 (2023) - [i84]Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser, Congyu Fang, Somesh Jha, Nicolas Papernot, Xiao Wang:
Robust and Actively Secure Serverless Collaborative Learning. CoRR abs/2310.16678 (2023) - [i83]Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Publicly Detectable Watermarking for Language Models. CoRR abs/2310.18491 (2023) - [i82]Xi Wu, Xiangyao Yu, Shaleen Deep, Ahmed Mahmood, Uyeong Jang, Stratis Viglas, Somesh Jha, John Cieslewicz, Jeffrey F. Naughton:
Bilevel Relations and Their Applications to Data Insights. CoRR abs/2311.04824 (2023) - [i81]Mingtian Tan, Tianhao Wang, Somesh Jha:
A Somewhat Robust Image Watermark against Diffusion-based Editing Models. CoRR abs/2311.13713 (2023) - [i80]Sanjam Garg, Aarushi Goel, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Guru-Vamsi Policharla, Mingyuan Wang:
Experimenting with Zero-Knowledge Proofs of Training. IACR Cryptol. ePrint Arch. 2023: 1345 (2023) - [i79]Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Publicly Detectable Watermarking for Language Models. IACR Cryptol. ePrint Arch. 2023: 1661 (2023) - 2022
- [j36]Vijay Ganesh, Sanjit A. Seshia, Somesh Jha:
Machine learning and logic: a new frontier in artificial intelligence. Formal Methods Syst. Des. 60(3): 426-451 (2022) - [j35]Zi Wang, Aws Albarghouthi, Gautam Prakriya, Somesh Jha:
Interval universal approximation for neural networks. Proc. ACM Program. Lang. 6(POPL): 1-29 (2022) - [c175]Samuel Maddock, Graham Cormode, Tianhao Wang, Carsten Maple, Somesh Jha:
Federated Boosted Decision Trees with Differential Privacy. CCS 2022: 2249-2263 - [c174]Amrita Roy Chowdhury, Bolin Ding, Somesh Jha, Weiran Liu, Jingren Zhou:
Strengthening Order Preserving Encryption with Differential Privacy. CCS 2022: 2519-2533 - [c173]Amrita Roy Chowdhury, Chuan Guo, Somesh Jha, Laurens van der Maaten:
EIFFeL: Ensuring Integrity for Federated Learning. CCS 2022: 2535-2549 - [c172]Mohannad Alhanahnah, Rithik Jain, Vaibhav Rastogi, Somesh Jha, Thomas W. Reps:
Lightweight, Multi-Stage, Compiler-Assisted Application Specialization. EuroS&P 2022: 251-269 - [c171]Ryan Feng, Neal Mangaokar, Jiefeng Chen, Earlence Fernandes, Somesh Jha, Atul Prakash:
GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems. EuroS&P 2022: 664-683 - [c170]Jiefeng Chen, Xi Wu, Yang Guo, Yingyu Liang, Somesh Jha:
Towards Evaluating the Robustness of Neural Networks Learned by Transduction. ICLR 2022 - [c169]Casey Meehan, Amrita Roy Chowdhury, Kamalika Chaudhuri, Somesh Jha:
Privacy Implications of Shuffling. ICLR 2022 - [c168]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Overparameterization from Computational Constraints. NeurIPS 2022 - [c167]Yizhen Wang, Mohannad Alhanahnah, Xiaozhu Meng, Ke Wang, Mihai Christodorescu, Somesh Jha:
Robust Learning against Relational Adversaries. NeurIPS 2022 - [c166]Zi Wang, Gautam Prakriya, Somesh Jha:
A Quantitative Geometric Approach to Neural-Network Smoothness. NeurIPS 2022 - [c165]Jordan Henkel, Goutham Ramakrishnan, Zi Wang, Aws Albarghouthi, Somesh Jha, Thomas W. Reps:
Semantic Robustness of Models of Source Code. SANER 2022: 526-537 - [i78]Harrison Rosenberg, Robi Bhattacharjee, Kassem Fawaz, Somesh Jha:
An Exploration of Multicalibration Uniform Convergence Bounds. CoRR abs/2202.04530 (2022) - [i77]Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash:
Towards Adversarially Robust Deepfake Detection: An Ensemble Approach. CoRR abs/2202.05687 (2022) - [i76]Aiping Xiong, Chuhao Wu, Tianhao Wang, Robert W. Proctor, Jeremiah Blocki, Ninghui Li, Somesh Jha:
Using Illustrations to Communicate Differential Privacy Trust Models: An Investigation of Users' Comprehension, Perception, and Data Sharing Decision. CoRR abs/2202.10014 (2022) - [i75]Zi Wang, Gautam Prakriya, Somesh Jha:
A Quantitative Geometric Approach to Neural Network Smoothness. CoRR abs/2203.01212 (2022) - [i74]Jihye Choi, Jayaram Raghuram, Ryan Feng, Jiefeng Chen, Somesh Jha, Atul Prakash:
Concept-based Explanations for Out-Of-Distribution Detectors. CoRR abs/2203.02586 (2022) - [i73]Saeed Mahloujifar, Alexandre Sablayrolles, Graham Cormode, Somesh Jha:
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms. CoRR abs/2204.06106 (2022) - [i72]Ryan Feng, Somesh Jha, Atul Prakash:
Constraining the Attack Space of Machine Learning Models with Distribution Clamping Preprocessing. CoRR abs/2205.08989 (2022) - [i71]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Overparameterized (robust) models from computational constraints. CoRR abs/2208.12926 (2022) - [i70]Samuel Maddock, Graham Cormode, Tianhao Wang, Carsten Maple, Somesh Jha:
Federated Boosted Decision Trees with Differential Privacy. CoRR abs/2210.02910 (2022) - [i69]Adam Dziedzic, Christopher A. Choquette-Choo, Natalie Dullerud, Vinith Menon Suriyakumar, Ali Shahin Shamsabadi, Muhammad Ahmad Kaleem, Somesh Jha, Nicolas Papernot, Xiao Wang:
Private Multi-Winner Voting for Machine Learning. CoRR abs/2211.15410 (2022) - [i68]Sébastien Bardin, Somesh Jha, Vijay Ganesh:
Machine Learning and Logical Reasoning: The New Frontier (Dagstuhl Seminar 22291). Dagstuhl Reports 12(7): 80-111 (2022) - 2021
- [j34]Kim G. Larsen, Natarajan Shankar, Pierre Wolper, Somesh Jha:
2018 CAV award. Formal Methods Syst. Des. 57(1): 116-117 (2021) - [j33]Varun Chandrasekaran, Chuhan Gao, Brian Tang, Kassem Fawaz, Somesh Jha, Suman Banerjee:
Face-Off: Adversarial Face Obfuscation. Proc. Priv. Enhancing Technol. 2021(2): 369-390 (2021) - [j32]Tianhao Wang, Ninghui Li, Somesh Jha:
Locally Differentially Private Heavy Hitter Identification. IEEE Trans. Dependable Secur. Comput. 18(2): 982-993 (2021) - [j31]Hassaan Irshad, Gabriela F. Ciocarlie, Ashish Gehani, Vinod Yegneswaran, Kyu Hyung Lee, Jignesh M. Patel, Somesh Jha, Yonghwi Kwon, Dongyan Xu, Xiangyu Zhang:
TRACE: Enterprise-Wide Provenance Tracking for Real-Time APT Detection. IEEE Trans. Inf. Forensics Secur. 16: 4363-4376 (2021) - [c164]Somesh Jha:
Trustworthy Machine Learning: Past, Present, and Future. AsiaCCS 2021: 1 - [c163]Tianhao Wang, Joann Qiongna Chen, Zhikun Zhang, Dong Su, Yueqiang Cheng, Zhou Li, Ninghui Li, Somesh Jha:
Continuous Release of Data Streams under both Centralized and Local Differential Privacy. CCS 2021: 1237-1253 - [c162]Washington Garcia, Animesh Chhotaray, Joseph I. Choi, Suman Kalyan Adari, Kevin R. B. Butler, Somesh Jha:
Brittle Features of Device Authentication. CODASPY 2021: 53-64 - [c161]Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang:
CaPC Learning: Confidential and Private Collaborative Learning. ICLR 2021 - [c160]Robi Bhattacharjee, Somesh Jha, Kamalika Chaudhuri:
Sample Complexity of Robust Linear Classification on Separated Data. ICML 2021: 884-893 - [c159]Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha, Suman Banerjee:
A General Framework For Detecting Anomalous Inputs to DNN Classifiers. ICML 2021: 8764-8775 - [c158]Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Guha Thakurta:
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks. NeurIPS 2021: 10862-10875 - [c157]Jiefeng Chen, Frederick Liu, Besim Avci, Xi Wu, Yingyu Liang, Somesh Jha:
Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles. NeurIPS 2021: 14980-14992 - [c156]Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha:
ATOM: Robustifying Out-of-Distribution Detection Using Outlier Mining. ECML/PKDD (3) 2021: 430-445 - [c155]Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta, Florian Tramèr:
Is Private Learning Possible with Instance Encoding? SP 2021: 410-427 - [i67]Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang:
CaPC Learning: Confidential and Private Collaborative Learning. CoRR abs/2102.05188 (2021) - [i66]Thomas Kobber Panum, Zi Wang, Pengyu Kan, Earlence Fernandes, Somesh Jha:
Exploring Adversarial Robustness of Deep Metric Learning. CoRR abs/2102.07265 (2021) - [i65]Washington Garcia, Pin-Yu Chen, Somesh Jha, Scott Clouse, Kevin R. B. Butler:
Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples. CoRR abs/2103.03325 (2021) - [i64]Varun Chandrasekaran, Darren Edge, Somesh Jha, Amit Sharma, Cheng Zhang, Shruti Tople:
Causally Constrained Data Synthesis for Private Data Release. CoRR abs/2105.13144 (2021) - [i63]Casey Meehan, Amrita Roy Chowdhury, Kamalika Chaudhuri, Somesh Jha:
A Shuffling Framework for Local Differential Privacy. CoRR abs/2106.06603 (2021) - [i62]Jiefeng Chen, Yang Guo, Xi Wu, Tianqi Li, Qicheng Lao, Yingyu Liang, Somesh Jha:
Towards Adversarial Robustness via Transductive Learning. CoRR abs/2106.08387 (2021) - [i61]Jiefeng Chen, Frederick Liu, Besim Avci, Xi Wu, Yingyu Liang, Somesh Jha:
Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles. CoRR abs/2106.15728 (2021) - [i60]Jayaram Raghuram, Yijing Zeng, Dolores García Martí, Somesh Jha, Suman Banerjee, Joerg Widmer, Rafael Ruiz Ortiz:
Domain Adaptation for Autoencoder-Based End-to-End Communication Over Wireless Channels. CoRR abs/2108.00874 (2021) - [i59]Harrison Rosenberg, Brian Tang, Kassem Fawaz, Somesh Jha:
Fairness Properties of Face Recognition and Obfuscation Systems. CoRR abs/2108.02707 (2021) - [i58]Nicholas Carlini, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Florian Tramèr:
NeuraCrypt is not private. CoRR abs/2108.07256 (2021) - [i57]Mohannad Alhanahnah, Rithik Jain, Vaibhav Rastogi, Somesh Jha, Thomas W. Reps:
Lightweight, Multi-Stage, Compiler-Assisted Application Specialization. CoRR abs/2109.02775 (2021) - [i56]Jiefeng Chen, Xi Wu, Yang Guo, Yingyu Liang, Somesh Jha:
Towards Evaluating the Robustness of Neural Networks Learned by Transduction. CoRR abs/2110.14735 (2021) - [i55]Amrita Roy Chowdhury, Chuan Guo, Somesh Jha, Laurens van der Maaten:
EIFFeL: Ensuring Integrity for Federated Learning. CoRR abs/2112.12727 (2021) - 2020
- [j30]Sanjit A. Seshia, Somesh Jha, Tommaso Dreossi:
Semantic Adversarial Deep Learning. IEEE Des. Test 37(2): 8-18 (2020) - [j29]Samuel Yeom, Irene Giacomelli, Alan Menaged, Matt Fredrikson, Somesh Jha:
Overfitting, robustness, and malicious algorithms: A study of potential causes of privacy risk in machine learning. J. Comput. Secur. 28(1): 35-70 (2020) - [j28]Tianhao Wang, Min Xu, Bolin Ding, Jingren Zhou, Cheng Hong, Zhicong Huang, Ninghui Li, Somesh Jha:
Improving Utility and Security of the Shuffler-based Differential Privacy. Proc. VLDB Endow. 13(13): 3545-3558 (2020) - [c154]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody:
Adversarially Robust Learning Could Leverage Computational Hardness. ALT 2020: 364-385 - [c153]Uyeong Jang, Susmit Jha, Somesh Jha:
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses. ICLR 2020 - [c152]Prasad Chalasani, Jiefeng Chen, Amrita Roy Chowdhury, Xi Wu, Somesh Jha:
Concise Explanations of Neural Networks using Adversarial Training. ICML 2020: 1383-1391 - [c151]Amrita Roy Chowdhury, Theodoros Rekatsinas, Somesh Jha:
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models. ICML 2020: 1939-1951 - [c150]Wei Zhang, Thomas Kobber Panum, Somesh Jha, Prasad Chalasani, David Page:
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods. ICML 2020: 11235-11245 - [c149]Amrita Roy Chowdhury, Chenghong Wang, Xi He, Ashwin Machanavajjhala, Somesh Jha:
Crypt?: Crypto-Assisted Differential Privacy on Untrusted Servers. SIGMOD Conference 2020: 603-619 - [c148]