{"list":"other","total":51,"rows":[{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1711.00851","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","created":"2017-11-02","cited_by_count":567},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"1811.00636","title":"Spectral Signatures in Backdoor Attacks","created":"2018-11-01","cited_by_count":484},{"id":"1708.06633","title":"Nonparametric regression using deep neural networks with ReLU activation function","created":"2017-08-22","cited_by_count":433},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1801.09344","title":"Certified Defenses against Adversarial Examples","created":"2018-01-29","cited_by_count":306},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"id":"1911.07135","title":"The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks","created":"2019-11-17","cited_by_count":246},{"id":"2306.09194","title":"Undetectable Watermarks for Language Models","created":"2023-05-25","cited_by_count":226},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"1512.03965","title":"The Power of Depth for Feedforward Neural Networks","created":"2015-12-12","cited_by_count":183},{"id":"2012.10544","title":"Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses","created":"2020-12-18","cited_by_count":180},{"id":"1709.07886","title":"Machine Learning Models that Remember Too Much","created":"2017-09-22","cited_by_count":169},{"id":"2104.11315","title":"SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics","created":"2021-04-22","cited_by_count":130},{"id":"2311.14455","title":"Universal Jailbreak Backdoors from Poisoned Human Feedback","created":"2023-11-24","cited_by_count":128},{"id":"1710.11278","title":"Approximating Continuous Functions by ReLU Nets of Minimal Width","created":"2017-10-31","cited_by_count":122},{"id":"1902.05040","title":"How do infinite width bounded norm networks look in function space?","created":"2019-02-13","cited_by_count":106},{"id":"2008.00312","title":"Trojaning Language Models for Fun and Profit","created":"2020-08-01","cited_by_count":90},{"id":"2111.00197","title":"Backdoor Pre-trained Models Can Transfer to All","created":"2021-10-30","cited_by_count":86},{"id":"1610.04161","title":"Why Deep Neural Networks for Function Approximation?","created":"2016-10-13","cited_by_count":82},{"id":"1805.10204","title":"Adversarial examples from computational constraints","created":"2018-05-25","cited_by_count":80},{"id":"2004.00622","title":"Evading Deepfake-Image Detectors with White- and Black-Box Attacks","created":"2020-04-01","cited_by_count":80},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63},{"id":"1610.09887","title":"Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks","created":"2016-10-31","cited_by_count":59},{"id":"2204.06974","title":"Planting Undetectable Backdoors in Machine Learning Models","created":"2022-04-14","cited_by_count":59},{"id":"2204.05239","title":"Exploring the Universal Vulnerability of Prompt-based Learning Paradigm","created":"2022-04-11","cited_by_count":57},{"id":"2210.14889","title":"Perfectly Secure Steganography Using Minimum Entropy Coupling","created":"2022-10-24","cited_by_count":44},{"id":"2402.09370","title":"Pseudorandom Error-Correcting Codes","created":"2024-02-14","cited_by_count":44},{"id":"2005.09595","title":"Continuous LWE","created":"2020-05-19","cited_by_count":37},{"id":"2004.02082","title":"On Tractable Representations of Binary Neural Networks","created":"2020-04-05","cited_by_count":34},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30},{"id":"2404.14461","title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs","created":"2024-04-22","cited_by_count":28},{"id":"2109.00685","title":"Excess Capacity and Backdoor Poisoning","created":"2021-09-02","cited_by_count":24},{"id":"2001.02992","title":"Poly-time universality and limitations of deep learning","created":"2020-01-07","cited_by_count":23},{"id":"2207.02842","title":"When does Bias Transfer in Transfer Learning?","created":"2022-07-06","cited_by_count":23},{"id":"2011.01929","title":"The Complexity of Gradient Descent: CLS = PPAD $\\cap$ PLS","created":"2020-11-03","cited_by_count":17},{"id":"1905.11564","title":"Adversarially Robust Learning Could Leverage Computational Hardness","created":"2019-05-28","cited_by_count":13},{"id":"2401.10360","title":"Excuse me, sir? Your language model is leaking (information)","created":"2024-01-18","cited_by_count":13},{"id":"2008.09317","title":"Indistinguishability Obfuscation from Well-Founded Assumptions","created":"2020-08-21","cited_by_count":12},{"id":"2106.08393","title":"Spoofing Generalization: When Can't You Trust Proprietary Models?","created":"2021-06-15","cited_by_count":2}],"next_cursor":null}