Related papers: Towards Realistic Guarantees: A Probabilistic Cert…
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…
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…
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…
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…
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}…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…