English
Related papers

Related papers: Towards Realistic Guarantees: A Probabilistic Cert…

200 papers

The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to…

Machine Learning · Computer Science 2021-04-20 Mamshad Nayeem Rizve , Kevin Duarte , Yogesh S Rawat , Mubarak Shah

Ensuring safety through set invariance has proven to be a valuable method in various robotics and control applications. This paper introduces a comprehensive framework for the safe probabilistic invariance verification of both discrete- and…

Systems and Control · Electrical Eng. & Systems 2024-08-06 Taoran Wu , Yiqing Yu , Bican Xia , Ji Wang , Bai Xue

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Machine Learning · Computer Science 2020-06-09 Jamie Hayes

Despite their impressive performance on diverse tasks, neural networks fail catastrophically in the presence of adversarial inputs---imperceptibly but adversarially perturbed versions of natural inputs. We have witnessed an arms race…

Machine Learning · Computer Science 2018-11-06 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, and {generalizing}…

Machine Learning · Computer Science 2022-09-19 Mengdi Xu , Zuxin Liu , Peide Huang , Wenhao Ding , Zhepeng Cen , Bo Li , Ding Zhao

The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensity to trust information from authoritative sources, such as…

Computation and Language · Computer Science 2025-07-21 Liang Lin , Zhihao Xu , Xuehai Tang , Shi Liu , Biyu Zhou , Fuqing Zhu , Jizhong Han , Songlin Hu

Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalability, judge imperfections, noise, and bias can invalidate…

Machine Learning · Computer Science 2026-01-30 Chen Feng , Minghe Shen , Ananth Balashankar , Carsten Gerner-Beuerle , Miguel R. D. Rodrigues

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning…

Machine Learning · Computer Science 2024-11-19 Junlin Wu , Huan Zhang , Yevgeniy Vorobeychik

Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety. Current robustness certificates for graph classifiers guarantee output invariance with respect to the total number of node pair flips…

Machine Learning · Computer Science 2023-06-27 Pierre Osselin , Henry Kenlay , Xiaowen Dong

As large language models evolve, Machine Unlearning has emerged to address growing concerns around user privacy, copyright infringement, and overall safety. Yet state-of-the-art (SOTA) unlearning methods often suffer from catastrophic…

Computation and Language · Computer Science 2026-03-31 Han Yan , Zheyuan Liu , Meng Jiang

ML models are typically trained using large datasets of high quality. However, training datasets often contain inconsistent or incomplete data. To tackle this issue, one solution is to develop algorithms that can check whether a prediction…

Machine Learning · Computer Science 2022-01-19 Austen Z. Fan , Paraschos Koutris

In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses consider additive threat models in which sample perturbations…

Machine Learning · Computer Science 2019-10-25 Alexander Levine , Soheil Feizi

The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustworthiness. Uncertainty quantification for LLMs can establish more human trust into their…

Computation and Language · Computer Science 2026-05-06 Daniel Yang , Yao-Hung Hubert Tsai , Makoto Yamada

In safety-critical deep learning applications, robustness measures the ability of neural models that handle imperceptible perturbations in input data, which may lead to potential safety hazards. Existing pre-deployment robustness assessment…

Machine Learning · Computer Science 2025-08-27 Wenchuan Mu , Kwan Hui Lim

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Cryptography and Security · Computer Science 2026-05-14 Zvi Topol

Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of jailbreak prompts, they often prove inadequate as jailbreak…

Cryptography and Security · Computer Science 2024-10-29 Tanqiu Jiang , Zian Wang , Jiacheng Liang , Changjiang Li , Yuhui Wang , Ting Wang

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

Cryptography and Security · Computer Science 2026-04-01 Zhuoran Tan , Jeremy Singer , Christos Anagnostopoulos

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Robotics · Computer Science 2020-03-10 Björn Lütjens , Michael Everett , Jonathan P. How

In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the…

Machine Learning · Computer Science 2024-06-13 Andrew C. Cullen , Shijie Liu , Paul Montague , Sarah M. Erfani , Benjamin I. P. Rubinstein

Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the…

Machine Learning · Computer Science 2021-11-18 Jongheon Jeong , Sejun Park , Minkyu Kim , Heung-Chang Lee , Doguk Kim , Jinwoo Shin