English
Related papers

Related papers: Towards Realistic Guarantees: A Probabilistic Cert…

200 papers

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Machine Learning · Computer Science 2024-06-17 Alexander Robey , Eric Wong , Hamed Hassani , George J. Pappas

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approaches do not provide…

Machine Learning · Computer Science 2025-11-11 Peter Blohm , Patrick Indri , Thomas Gärtner , Sagar Malhotra

This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these…

Cryptography and Security · Computer Science 2024-10-10 Tomas Bueno Momcilovic , Dian Balta , Beat Buesser , Giulio Zizzo , Mark Purcell

In this paper, we investigate the probabilistic formal verification of stochastic dynamical systems over continuous state spaces. Motivated by problems in state estimation and information-flow security, we introduce the notion of…

Systems and Control · Electrical Eng. & Systems 2026-04-07 Bohan Cui , Jianing Zhao , Yu Chen , Alessandro Abate , Marta Kwiatkowska , Xiang Yin

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…

Machine Learning · Computer Science 2022-02-03 Michael Everett , Bjorn Lutjens , Jonathan P. How

Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarantees. Providing formal guarantees for such models is hard because "harmful…

Machine Learning · Computer Science 2026-05-12 Nikita Kezins , Urbas Ekka , Pascal Berrang , Luca Arnaboldi

Algorithmic verification of realistic systems to satisfy safety and other temporal requirements has suffered from poor scalability of the employed formal approaches. To design systems with rigorous guarantees, many approaches still rely on…

Systems and Control · Electrical Eng. & Systems 2024-03-18 Oliver Schön , Zhengang Zhong , Sadegh Soudjani

Vanilla Reinforcement Learning (RL) can efficiently solve complex tasks but does not provide any guarantees on system behavior. To bridge this gap, we propose a three-step safe RL procedure for continuous action spaces that provides…

Robotics · Computer Science 2023-09-29 Hanna Krasowski , Prithvi Akella , Aaron D. Ames , Matthias Althoff

Stability guarantees have emerged as a principled way to evaluate feature attributions, but existing certification methods rely on heavily smoothed classifiers and often produce conservative guarantees. To address these limitations, we…

Machine Learning · Computer Science 2025-08-08 Helen Jin , Anton Xue , Weiqiu You , Surbhi Goel , Eric Wong

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…

Machine Learning · Computer Science 2019-01-08 Tsui-Wei Weng , Pin-Yu Chen , Lam M. Nguyen , Mark S. Squillante , Ivan Oseledets , Luca Daniel

We argue that when it comes to producing secure code with AI, the prevailing "fighting fire with fire" approach -- using probabilistic AI-based checkers or attackers to secure probabilistically generated code -- fails to address the long…

Cryptography and Security · Computer Science 2026-02-10 Benjamin Livshits

As ML models are increasingly deployed in critical applications, robustness against adversarial perturbations is crucial. While numerous defenses have been proposed to counter such attacks, they typically assume that all adversarial…

Machine Learning · Computer Science 2025-06-11 Yuan Xin , Dingfan Chen , Michael Backes , Xiao Zhang

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we…

Computation and Language · Computer Science 2025-12-19 Stephen Obadinma , Xiaodan Zhu

Large language models often produce confident but incorrect outputs, creating a critical need for reliable uncertainty quantification with formal abstention guarantees. We introduce information-lift certificates that compare model…

Machine Learning · Computer Science 2025-11-20 Sanjeda Akter , Ibne Farabi Shihab , Anuj Sharma

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…

Machine Learning · Statistics 2025-03-26 Edwin Hamel-De le Court , Francesco Belardinelli , Alexander W. Goodall

This paper presents a methodology for temporal logic verification of discrete-time stochastic systems. Our goal is to find a lower bound on the probability that a complex temporal property is satisfied by finite traces of the system.…

Systems and Control · Computer Science 2019-11-22 Pushpak Jagtap , Sadegh Soudjani , Majid Zamani

Many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data. However, existing control techniques often assume access to…

Systems and Control · Electrical Eng. & Systems 2025-06-24 Haoming Jing , Yorie Nakahira

We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate the robustness…

Machine Learning · Computer Science 2022-07-12 Hanbin Hong , Binghui Wang , Yuan Hong

The deployment of Large Language Models (LLMs) in robotic systems presents unique safety challenges, particularly in unpredictable environments. Although LLMs, leveraging zero-shot learning, enhance human-robot interaction and…

Robotics · Computer Science 2025-03-07 Ahmad Hafez , Alireza Naderi Akhormeh , Amr Hegazy , Amr Alanwar
‹ Prev 1 2 3 10 Next ›