Unlocking The Potential of Adaptive Attacks on Diffusion-Based Purification

• URL: http://arxiv.org/abs/2411.16598v1
• Date: Mon, 25 Nov 2024 17:30:32 GMT
• Title: Unlocking The Potential of Adaptive Attacks on Diffusion-Based Purification
• Authors: Andre Kassis, Urs Hengartner, Yaoliang Yu,
• Abstract summary: Diffusion-based purification (DBP) is a defense against adversarial examples (AEs) We revisit this claim, focusing on gradient-based strategies that back-propagate the loss gradients through the defense. We show that such an optimization method invalidates DBP's core foundations and restricts the purified outputs to a distribution over malicious samples instead.
• Score: 20.15955997832192
• License:
• Abstract: Diffusion-based purification (DBP) is a defense against adversarial examples (AEs), amassing popularity for its ability to protect classifiers in an attack-oblivious manner and resistance to strong adversaries with access to the defense. Its robustness has been claimed to ensue from the reliance on diffusion models (DMs) that project the AEs onto the natural distribution. We revisit this claim, focusing on gradient-based strategies that back-propagate the loss gradients through the defense, commonly referred to as ``adaptive attacks". Analytically, we show that such an optimization method invalidates DBP's core foundations, effectively targeting the DM rather than the classifier and restricting the purified outputs to a distribution over malicious samples instead. Thus, we reassess the reported empirical robustness, uncovering implementation flaws in the gradient back-propagation techniques used thus far for DBP. We fix these issues, providing the first reliable gradient library for DBP and demonstrating how adaptive attacks drastically degrade its robustness. We then study a less efficient yet stricter majority-vote setting where the classifier evaluates multiple purified copies of the input to make its decision. Here, DBP's stochasticity enables it to remain partially robust against traditional norm-bounded AEs. We propose a novel adaptation of a recent optimization method against deepfake watermarking that crafts systemic malicious perturbations while ensuring imperceptibility. When integrated with the adaptive attack, it completely defeats DBP, even in the majority-vote setup. Our findings prove that DBP, in its current state, is not a viable defense against AEs.

Related papers

• ADBM: Adversarial diffusion bridge model for reliable adversarial purification [21.2538921336578]
  Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. We find DiffPure which directly employs the original pre-trained diffusion models for adversarial purification to be suboptimal. We propose a novel Adrialversa Diffusion Bridge Model, termed ADBM, which constructs a reverse bridge from diffused adversarial data back to its original clean examples.
  arXiv  Detail & Related papers  (2024-08-01T06:26:05Z)
• Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective [65.10019978876863]
  Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks. In this paper, we argue that the inherentity in the DBP process is the primary driver of its robustness.
  arXiv  Detail & Related papers  (2024-04-22T16:10:38Z)
• DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification [63.65630243675792]
  Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples. Recent studies show that even advanced attacks cannot break such defenses effectively. We propose a unified framework DiffAttack to perform effective and efficient attacks against diffusion-based purification defenses.
  arXiv  Detail & Related papers  (2023-10-27T15:17:50Z)
• Confidence-driven Sampling for Backdoor Attacks [49.72680157684523]
  Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing trigger stealthiness while randomly selecting poisoned samples. We introduce a straightforward yet highly effective sampling methodology that leverages confidence scores. Specifically, it selects samples with lower confidence scores, significantly increasing the challenge for defenders in identifying and countering these attacks.
  arXiv  Detail & Related papers  (2023-10-08T18:57:36Z)
• LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack [11.764601181046496]
  Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model outputs. We propose a simple yet effective disruption method called Latent Ensemble ATtack (LEAT), which attacks the independent latent encoding process.
  arXiv  Detail & Related papers  (2023-07-04T07:00:37Z)
• Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation [122.83280749890078]
  We propose an improved certified defense against general poisoning attacks, namely Finite Aggregation. In contrast to DPA, which directly splits the training set into disjoint subsets, our method first splits the training set into smaller disjoint subsets. We offer an alternative view of our method, bridging the designs of deterministic and aggregation-based certified defenses.
  arXiv  Detail & Related papers  (2022-02-05T20:08:58Z)
• Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses [22.531976474053057]
  Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks. We propose Scale-Invariant Adversarial Attack (SI-PGD), which utilizes the angle between the features in the penultimate layer and the weights in the softmax layer to guide the generation of adversaries.
  arXiv  Detail & Related papers  (2022-01-29T08:40:53Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)
• A Self-supervised Approach for Adversarial Robustness [105.88250594033053]
  Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems. This paper proposes a self-supervised adversarial training mechanism in the input space. It provides significant robustness against the textbfunseen adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-08T20:42:39Z)

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.