Related papers: Set-level Guidance Attack: Boosting Adversarial Tr…
Different from traditional task-specific vision models, recent large VLMs can readily adapt to different vision tasks by simply using different textual instructions, i.e., prompts. However, a well-known concern about traditional…
Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…
Recent studies have revealed that modern image and video quality assessment (IQA/VQA) metrics are vulnerable to adversarial attacks. An attacker can manipulate a video through preprocessing to artificially increase its quality score…
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…
Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability…
Although vision-language pre-training (VLP) models have achieved remarkable progress on cross-modal tasks, they remain vulnerable to adversarial attacks. Using data augmentation and cross-modal interactions to generate transferable…
Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static settings, this paper explores backdoor attacks in LVLM…
Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studies have shown they are vulnerable to maliciously crafted…
Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the…
Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs…
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…
Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the existing settings of NMT targeted adversarial attacks, where…
Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks…
Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…
Vision-language-action (VLA) models have significantly advanced robotic learning, enabling training on large-scale, cross-embodiment data and fine-tuning for specific robots. However, state-of-the-art autoregressive VLAs struggle with…
Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification performance on natural examples), we investigate and identify…
Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…
Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the adversarial perturbation. Prior work in this direction often…
Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…