Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers

• URL: http://arxiv.org/abs/2405.10612v1
• Date: Fri, 17 May 2024 08:19:48 GMT
• Title: Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
• Authors: Sheng Yang, Jiawang Bai, Kuofeng Gao, Yong Yang, Yiming Li, Shu-tao Xia,
• Abstract summary: An extra prompt token, called the switch token in this work, can turn the backdoor mode on, converting a benign model into a backdoored one. To attack a pre-trained model, our proposed attack, named SWARM, learns a trigger and prompt tokens including a switch token. Experiments on diverse visual recognition tasks confirm the success of our switchable backdoor attack, achieving 95%+ attack success rate.
• Score: 51.0477382050976
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat towards such a paradigm from the perspective of backdoor attacks. Specifically, an extra prompt token, called the switch token in this work, can turn the backdoor mode on, i.e., converting a benign model into a backdoored one. Once under the backdoor mode, a specific trigger can force the model to predict a target class. It poses a severe risk to the users of cloud API, since the malicious behavior can not be activated and detected under the benign mode, thus making the attack very stealthy. To attack a pre-trained model, our proposed attack, named SWARM, learns a trigger and prompt tokens including a switch token. They are optimized with the clean loss which encourages the model always behaves normally even the trigger presents, and the backdoor loss that ensures the backdoor can be activated by the trigger when the switch is on. Besides, we utilize the cross-mode feature distillation to reduce the effect of the switch token on clean samples. The experiments on diverse visual recognition tasks confirm the success of our switchable backdoor attack, i.e., achieving 95%+ attack success rate, and also being hard to be detected and removed. Our code is available at https://github.com/20000yshust/SWARM.

Related papers

• Backdoor Attack with Sparse and Invisible Trigger [57.41876708712008]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. backdoor attack is an emerging yet threatening training-phase threat. We propose a sparse and invisible backdoor attack (SIBA)
  arXiv  Detail & Related papers  (2023-05-11T10:05:57Z)
• BATT: Backdoor Attack with Transformation-based Triggers [72.61840273364311]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. Backdoor adversaries inject hidden backdoors that can be activated by adversary-specified trigger patterns. One recent research revealed that most of the existing attacks failed in the real physical world.
  arXiv  Detail & Related papers  (2022-11-02T16:03:43Z)
• Dual-Key Multimodal Backdoors for Visual Question Answering [26.988750557552983]
  We show that multimodal networks are vulnerable to a novel type of attack that we refer to as Dual-Key Multimodal Backdoors. This attack exploits the complex fusion mechanisms used by state-of-the-art networks to embed backdoors that are both effective and stealthy. We present an extensive study of multimodal backdoors on the Visual Question Answering (VQA) task with multiple architectures and visual feature backbones.
  arXiv  Detail & Related papers  (2021-12-14T18:59:52Z)
• Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch [99.90716010490625]
  Backdoor attackers tamper with training data to embed a vulnerability in models that are trained on that data. This vulnerability is then activated at inference time by placing a "trigger" into the model's input. We develop a new hidden trigger attack, Sleeper Agent, which employs gradient matching, data selection, and target model re-training during the crafting process.
  arXiv  Detail & Related papers  (2021-06-16T17:09:55Z)
• Backdoor Attack in the Physical World [49.64799477792172]
  Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs) Most existing backdoor attacks adopted the setting of static trigger, $i.e.,$ triggers across the training and testing images. We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.
  arXiv  Detail & Related papers  (2021-04-06T08:37:33Z)
• Input-Aware Dynamic Backdoor Attack [9.945411554349276]
  In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Current backdoor techniques rely on uniform trigger patterns, which are easily detected and mitigated by current defense methods. We propose a novel backdoor attack technique in which the triggers vary from input to input.
  arXiv  Detail & Related papers  (2020-10-16T03:57:12Z)
• Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks [22.28270345106827]
  Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a trigger to it, for the target model to activate the backdoor. This added trigger not only increases the difficulty of launching the backdoor attack in the physical world, but also can be easily detected by multiple defense mechanisms. We present the first triggerless backdoor attack against deep neural networks, where the adversary does not need to modify the input for triggering the backdoor.
  arXiv  Detail & Related papers  (2020-10-07T09:01:39Z)
• Rethinking the Trigger of Backdoor Attack [83.98031510668619]
  Currently, most of existing backdoor attacks adopted the setting of emphstatic trigger, $i.e.,$ triggers across the training and testing images follow the same appearance and are located in the same area. We demonstrate that such an attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.
  arXiv  Detail & Related papers  (2020-04-09T17:19:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.