Related papers: DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks i…

A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model deployments. State-of-the-art defenses are either limited to…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge…

The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more…

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision…

Reliable confidence estimation is critical when deploying vision models. We study error prediction: determining whether an image classifier's output is correct using only signals from a single forward pass. Motivated by internal-signal…

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…

Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstrated the vulnerability of deep hashing models to backdoor…

Deep learning models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Even this poses a serious security challenge for the localization of self-driving cars, there has been very little…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Data augmentation is used extensively to improve model generalisation. However, reliance on external libraries to implement augmentation methods introduces a vulnerability into the machine learning pipeline. It is well known that backdoors…

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning.…

Vision Transformers (ViTs) have demonstrated superior performance over Convolutional Neural Networks (CNNs) in various vision-related tasks such as classification, object detection, and segmentation due to their use of self-attention…

Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with. A well-known vulnerability is a backdoor introduced into a…

In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first categorize backdoor triggers from a new perspective, i.e.,…

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the…

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…