Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors during training, which are activated by specific triggers during inference, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the malicious impacts of such attacks, these defenses frequently necessitate extensive training time and degrade clean accuracy. In this study, we propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities, known as Unlearn Backdoor Threats (UBT). We specifically use overfit training to improve backdoor shortcuts and accurately detect suspicious samples in the potential poisoning data set. Then, we select fewer unlearned samples from suspicious samples for rapid forgetting in order to eliminate the backdoor effect and thus improve backdoor defense efficiency. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime. This technique focuses on the model's compromised elements, dissociating backdoor correlations while maintaining the model's overall integrity. Extensive experimental results show that our method effectively defends against various backdoor attack methods in the CLIP model. Compared to SoTA backdoor defense methods, UBT achieves the lowest attack success rate while maintaining a high clean accuracy of the model (attack success rate decreases by 19% compared to SOTA, while clean accuracy increases by 2.57%).

Adversarial Backdoor Defense in CLIP

Multimodal contrastive pretraining, exemplified by models like CLIP, has been found to be vulnerable to backdoor attacks. While current backdoor defense methods primarily employ conventional data augmentation to create augmented samples aimed at feature alignment, these methods fail to capture the distinct features of backdoor samples, resulting in suboptimal defense performance. Observations reveal that adversarial examples and backdoor samples exhibit similarities in the feature space within the compromised models. Building on this insight, we propose Adversarial Backdoor Defense (ABD), a novel data augmentation strategy that aligns features with meticulously crafted adversarial examples. This approach effectively disrupts the backdoor association. Our experiments demonstrate that ABD provides robust defense against both traditional uni-modal and multimodal backdoor attacks targeting CLIP. Compared to the current state-of-the-art defense method, CleanCLIP, ABD reduces the attack success rate by 8.66% for BadNet, 10.52% for Blended, and 53.64% for BadCLIP, while maintaining a minimal average decrease of just 1.73% in clean accuracy.

Revisiting Backdoor Attacks against Large Vision-Language Models

Instruction tuning enhances large vision-language models (LVLMs) but raises security risks through potential backdoor attacks due to their openness. Previous backdoor studies focus on enclosed scenarios with consistent training and testing instructions, neglecting the practical domain gaps that could affect attack effectiveness. This paper empirically examines the generalizability of backdoor attacks during the instruction tuning of LVLMs for the first time, revealing certain limitations of most backdoor strategies in practical scenarios. We quantitatively evaluate the generalizability of six typical backdoor attacks on image caption benchmarks across multiple LVLMs, considering both visual and textual domain offsets. Our findings indicate that attack generalizability is positively correlated with the backdoor trigger's irrelevance to specific images/models and the preferential correlation of the trigger pattern. Additionally, we modify existing backdoor attacks based on the above key observations, demonstrating significant improvements in cross-domain scenario generalizability (+86% attack success rate). Notably, even without access to the instruction datasets, a multimodal instruction set can be successfully poisoned with a very low poisoning rate (0.2%), achieving an attack success rate of over 97%. This paper underscores that even simple traditional backdoor strategies pose a serious threat to LVLMs, necessitating more attention and in-depth research.

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the possibility of backdoor attacks. These attacks subtly embed malicious behaviors within the model during training, which can be activated by specific triggers in the inference phase, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the adverse impacts of such attacks, these defenses often degrade the clean accuracy and necessitate the construction of extensive clean training pairs. In this paper, we explore the possibility of a less-cost defense from the perspective of model unlearning, that is, whether the model can be made to quickly \textbf{u}nlearn \textbf{b}ackdoor \textbf{t}hreats (UBT) by constructing a small set of poisoned samples. Specifically, we strengthen the backdoor shortcuts to discover suspicious samples through overfitting training prioritized by weak similarity samples. Building on the initial identification of suspicious samples, we introduce an innovative token-based localized forgetting training regime. This technique specifically targets the poisoned aspects of the model, applying a focused effort to unlearn the backdoor associations and trying not to damage the integrity of the overall model. Experimental results show that our method not only ensures a minimal success rate for attacks, but also preserves the model's high clean accuracy.

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However, we uncover the potential threat posed by backdoor attacks on autoregressive VLMs during instruction tuning. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images, enabling malicious manipulation of the victim model's predictions with predefined triggers. Nevertheless, the frozen visual encoder in autoregressive VLMs imposes constraints on the learning of conventional image triggers. Additionally, adversaries may encounter restrictions in accessing the parameters and architectures of the victim model. To address these challenges, we propose a multimodal instruction backdoor attack, namely VL-Trojan. Our approach facilitates image trigger learning through an isolating and clustering strategy and enhance black-box-attack efficacy via an iterative character-level text trigger generation method. Our attack successfully induces target outputs during inference, significantly surpassing baselines (+62.52\%) in ASR. Moreover, it demonstrates robustness across various model scales and few-shot in-context reasoning scenarios.

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

The proliferation of face forgery techniques has raised significant concerns within society, thereby motivating the development of face forgery detection methods. These methods aim to distinguish forged faces from genuine ones and have proven effective in practical applications. However, this paper introduces a novel and previously unrecognized threat in face forgery detection scenarios caused by backdoor attack. By embedding backdoors into models and incorporating specific trigger patterns into the input, attackers can deceive detectors into producing erroneous predictions for forged faces. To achieve this goal, this paper proposes \emph{Poisoned Forgery Face} framework, which enables clean-label backdoor attacks on face forgery detectors. Our approach involves constructing a scalable trigger generator and utilizing a novel convolving process to generate translation-sensitive trigger patterns. Moreover, we employ a relative embedding method based on landmark-based regions to enhance the stealthiness of the poisoned samples. Consequently, detectors trained on our poisoned samples are embedded with backdoors. Notably, our approach surpasses SoTA backdoor baselines with a significant improvement in attack success rate (+16.39\% BD-AUC) and reduction in visibility (-12.65\% $L_\infty$). Furthermore, our attack exhibits promising performance against backdoor defenses. We anticipate that this paper will draw greater attention to the potential threats posed by backdoor attacks in face forgery detection scenarios. Our codes will be made available at \url{https://github.com/JWLiang007/PFF}

Rethinking Data Augmentation in Knowledge Distillation for Object Detection

Knowledge distillation (KD) has shown its effectiveness for object detection, where it trains a compact object detector under the supervision of both AI knowledge (teacher detector) and human knowledge (human expert). However, existing studies treat the AI knowledge and human knowledge consistently and adopt a uniform data augmentation strategy during learning, which would lead to the biased learning of multi-scale objects and insufficient learning for the teacher detector causing unsatisfactory distillation performance. To tackle these problems, we propose the sample-specific data augmentation and adversarial feature augmentation. Firstly, to mitigate the impact incurred by multi-scale objects, we propose an adaptive data augmentation based on our observations from the Fourier perspective. Secondly, we propose a feature augmentation method based on adversarial examples for better mimicking AI knowledge to make up for the insufficient information mining of the teacher detector. Furthermore, our proposed method is unified and easily extended to other KD methods. Extensive experiments demonstrate the effectiveness of our framework and improve the performance of state-of-the-art methods in one-stage and two-stage detectors, bringing at most 0.5 mAP gains.