相关论文: Robustness Evaluation of Transformer-based Form Fi…

Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even with the same intent,…

Neural network models have become the leading solution for a large variety of tasks, such as classification, language processing, protein folding, and others. However, their reliability is heavily plagued by adversarial inputs: small input…

Offline safe RL is of great practical relevance for deploying agents in real-world applications. However, acquiring constraint-satisfying policies from the fixed dataset is non-trivial for conventional approaches. Even worse, the learned…

Understanding how cells respond to external stimuli is a central challenge in biomedical research and drug development. Current computational frameworks for modelling cellular responses remain restricted to two-dimensional representations,…

The existence of real-world adversarial examples (commonly in the form of patches) poses a serious threat for the use of deep learning models in safety-critical computer vision tasks such as visual perception in autonomous driving. This…

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Both transduction and rejection have emerged as important techniques for defending against adversarial perturbations. A recent work by Goldwasser et al. showed that rejection combined with transduction can give provable guarantees (for…

Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious…

Face-morphing attacks have been a cause for concern for a number of years. Striving to remain one step ahead of attackers, researchers have proposed many methods of both creating and detecting morphed images. These detection methods,…

Several recent works have developed methods for training classifiers that are certifiably robust against norm-bounded adversarial perturbations. These methods assume that all the adversarial transformations are equally important, which is…

In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. Attack detection models can be leveraged to provide an additional check for NLP models and…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may contain input noise caused by text extraction artifacts or…

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…

Large language models (LLMs) are very costly and inefficient to update with new information. To address this limitation, retrieval-augmented generation (RAG) has been proposed as a solution that dynamically incorporates external knowledge…

This paper studies the adversarial robustness of conformal novelty detection. In particular, we focus on two powerful learning-based frameworks that come with finite-sample false discovery rate (FDR) control: one is AdaDetect (by Marandon…

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement…

Recent unified multi-modal encoders align a wide range of modalities into a shared representation space, enabling diverse cross-modal tasks. Despite their impressive capabilities, the robustness of these models under adversarial…