48 accepted papers
Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs, causing users to accept erroneous answers without statistical guarantees. We address this through the lens of false discovery rate (FDR) control, ensu…
Uncertainty quantification (UQ) in foundation models is crucial for identifying and mitigating hallucinations in automatically generated text. However, heuristic UQ approaches lack statistical guarantees for key metrics such as the false discovery rate (FDR) in selective prediction tasks. Previous
Large language models (LLMs) increasingly rely on Chain-of-Thought (CoT) prompting to improve problem-solving and provide seemingly transparent explanations. However, growing evidence shows that CoT often fail to faithfully represent the underlying reasoning process, raising concerns about their rel…
Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority voting, which ignores PRM signals, occasionally outperforms st…
Benchmarks establish a standardized evaluation framework to systematically assess the performance of large language models (LLMs), facilitating objective comparisons and driving advancements in the field. However, existing benchmarks fail to differentiate question difficulty, limiting their ability…
With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) can effectively reduc
Humans express uncertainty verbally via markers (e.g., "possible", "likely"), yet most LLM uncertainty quantification (UQ) relies on costing likelihood- or consistency-based signals. From a cognitive perspective, accurate verbal uncertainty reflects metacognitive monitoring, representing knowledge b…
Current text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images. To address this, various safety mechanisms and red teaming attack methods are proposed to enhance or expose the T2I model’s capability to generate uns…
The rapid advancement of large language models (LLMs) has significantly improved their performance in code generation tasks. However, existing code benchmarks remain static, consisting of fixed datasets with predefined problems. This makes them vulnerable to memorization during training, where LLMs…
Although Large Language Models (LLMs) succeed in human-guided conversations such as instruction following and question answering, the potential of LLM-guided conversations—where LLMs direct the discourse and steer the conversation’s objectives—remains under-explored. In this study, we first characte…
Advancements in Large Language Models (LLMs) and their increasing use in medical question-answering necessitate rigorous evaluation of their reliability. A critical challenge lies in hallucination, where models generate plausible yet factually incorrect outputs. In the medical domain, this poses ser
Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images containing inappropriate content by simply editing the language moda…
Mixture of Experts (MoE) have shown remarkable success in leveraging specialized expert networks for complex machine learning tasks. However, their susceptibility to adversarial attacks presents a critical challenge for deployment in robust applications. This paper addresses the critical question of…
As large language models are increasingly utilized in real-world applications, guarantees of task-specific metrics are essential for their reliable deployment. Previous studies have introduced various criteria of conformal uncertainty grounded in split conformal prediction, which offer user-specifie…
Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded in the internal representations of LLMs and can be both detected and controlled a
Object Hallucination (OH) has been acknowledged as one of the major trustworthy challenges in Large Vision-Language Models (LVLMs). Recent advancements in Large Language Models (LLMs) indicate that internal states, such as hidden states, encode the "overall truthfulness" of generated responses. Howe…
Though diffusion models excel in image generation their step-by-step denoising leads to slow generation speeds. Consistency training addresses this issue with single-step sampling but often produces lower-quality generations and requires high training costs. In this paper we show that optimizing con…
Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an efficient query-based membership inference attack (MIA), namely Pro…
Stable Diffusion has established itself as a foundation model in generative AI artistic applications receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant personalized concepts onto the basic Stable Diffusion model with minima…
Uncertainty quantification (UQ) in natural language generation (NLG) tasks remains an open challenge, exacerbated by the closed-source nature of the latest large language models (LLMs). This study investigates applying conformal prediction (CP), which can transform any heuristic uncertainty notion i…
Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety a…
This paper introduces an attacking mechanism to challenge the resilience of autonomous driving systems. Specifically, we manipulate the decision-making processes of an autonomous vehicle by dynamically displaying adversarial patches on a screen mounted on another moving vehicle. These patches are op…
As Large Language Models (LLMs) are integrated into critical real-world applications, their strategic and logical reasoning abilities are increasingly crucial. This paper evaluates LLMs' reasoning abilities in competitive environments through game-theoretic tasks, e.g., board and card games that req…
We present NN4SysBench, a benchmark suite for neural network verification that is composed of applications from the domain of computer systems. We call these neural networks for computer systems or NN4Sys. NN4Sys is booming: there are many proposals for using neural networks in computer systems—for…
Large language models (LLMs) have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLM…
Current logical reasoning evaluations of Large Language Models (LLMs) primarily focus on single-turn and static environments, such as arithmetic problems. The crucial problem of multi-turn, strategic reasoning is under-explored. In this work, we analyze the multi-turn strategic reasoning of LLMs thr…
Large Language Models (LLMs) show promising results in language generation and instruction following but frequently “hallucinate”, making their outputs less reliable. Despite Uncertainty Quantification’s (UQ) potential solutions, implementing it accurately within LLMs is challenging. Our research in…
The open sourcing of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these image datasets being exploited by unauthorized third parties to train deep learning models for commercial or illegal purposes. To avoid the abuse of…
"Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which disrupt Vision-Language Models (VLMs) such as Contrastive Lang…
Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we investigate the vulnerability of diffusion models to Membership Inference Attacks (MIAs), a common privacy concern. Our…
In autonomous driving (AD), accurate perception is indispensable to achieving safe and secure driving. Due to its safety-criticality, the security of AD perception has been widely studied. Among different attacks on AD perception, the physical adversarial object evasion attacks are especially severe…
Recent works reveal that adversarial augmentation benefits the generalization of neural networks (NNs) if used in an appropriate manner. In this paper, we introduce Temporal Adversarial Augmentation (TA), a novel video augmentation technique that utilizes temporal attention. Unlike conventional adve…
Strong adversarial attacks are important for evaluating the true robustness of deep neural networks. Most existing attacks search in the input space, e.g., using gradient descent, and may miss adversarial examples due to non-convexity. In this work, we systematically search adversarial examples in t…
Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robustness, and safety. However, existing works cannot handle the general form of cutting plane constraints widely accepted…
As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical applications, the security concerns in SNNs attract more attention. Currently, researchers have already demonstrated an SNN can be attacked with adversarial examples. How to build a robust SNN becomes an u…
Bound propagation based incomplete neural network verifiers such as CROWN are very efficient and can significantly accelerate branch-and-bound (BaB) based complete verification of neural networks. However, bound propagation cannot fully handle the neuron split constraints introduced by BaB commonly…
Formal verification of neural networks (NNs) is a challenging and important problem. Existing efficient complete solvers typically require the branch-and-bound (BaB) process, which splits the problem domain into sub-domains and solves each sub-domain using faster but weaker incomplete verifiers, suc…
Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. It enables us to learn a $\textit{meta-initialization}$ of model parameters (that we call $\textit{meta-model}$) to rapidly adapt to new tasks using a small amount of labeled…
Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial patch attacks work well on small images like MNIST and CIFAR-10…
It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decision makers by attaching adversarial patches to real objects. However, most of the existing works on physical adversarial attacks focus on static obje…
Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense. The majority of LiRPA-based methods focus on…
Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade-off between the source domain and the target domain. In this work, instead…
In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimat…
Graph Neural Networks (GNNs) have made significant advances on several fundamental inference tasks. As a result, there is a surge of interest in using these models for making potentially important decisions in high-regret applications. However, despite GNNs' impressive performance, it has been obser…
It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training can provide a notion of security against adversarial attacks. However, adversari…
Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations. Despite the long-term vision, however, existing studies on black-box…
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks perturbing the raw input spaces may fail to capture structural inf…
The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optimization methods for solving machine learning problems. However, AdaMM is not suited for solving black-box optimization…