Related papers: See No Evil: Adversarial Attacks Against Linguisti…

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is…

Building on the unprecedented capabilities of large language models for command understanding and zero-shot recognition of multi-modal vision-language transformers, visual language navigation (VLN) has emerged as an effective way to address…

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

Transformer models have excelled in natural language tasks, prompting the vision community to explore their implementation in computer vision problems. However, these models are still influenced by adversarial examples. In this paper, we…

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an open challenge. In…

Multimodal learning has shown significant superiority on various tasks by integrating multiple modalities. However, the interdependencies among modalities increase the susceptibility of multimodal models to adversarial attacks. Existing…

Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Adversarial robustness of BEV 3D object detectors is critical for autonomous driving (AD). Existing invasive attacks require altering the target vehicle itself (e.g. attaching patches), making them unrealistic and impractical for real-world…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algorithm for evaluating the robustness of object-detection DL…

With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional…

We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…

As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand,…

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the…

In the last decade, the use of Machine Learning techniques in anomaly-based intrusion detection systems has seen much success. However, recent studies have shown that Machine learning in general and deep learning specifically are vulnerable…

Assuring the safety and trustworthiness of autonomous systems is particularly difficult when learning-enabled components and open environments are involved. Formal methods provide strong guarantees but depend on complete models and static…