An official website of the United States government
In a black-box setting, the adversary only has API access to the target model and each query is expensive. Prior work on black-box adversarial examples follows one of two main strategies: (1) transfer attacks use white-box attacks on local models to find candidate adversarial examples that transfer to the target model, and (2) optimization-based attacks use queries to the target model and apply optimization techniques to search for adversarial examples. We propose hybrid attacks that combine both strategies, using candidate adversarial examples from local models as starting points for optimization-based attacks and using labels learned in optimization-based attacks to tune local models for finding transfer candidates. We empirically demonstrate on the MNIST, CIFAR10, and ImageNet datasets that our hybrid attack strategy reduces cost and improves success rates, and in combination with our seed prioritization strategy, enables batch attacks that can efficiently find adversarial examples with only a handful of queries.
more »
« less
Evaluating Robustness of Sequence-based Deepfake Detector Models by Adversarial Perturbation
Deepfake videos are getting better in quality and can be used for dangerous disinformation campaigns. The pressing need to detect these videos has motivated researchers to develop different types of detection models. Among them, the models that utilize temporal information (i.e., sequence-based models) are more effective at detection than the ones that only detect intra-frame discrepancies. Recent work has shown that the latter detection models can be fooled with adversarial examples, leveraging the rich literature on crafting adversarial (still) images. It is less clear, however, how well these attacks will work on sequence-based models that operate on information taken over multiple frames. In this paper, we explore the effectiveness of the Fast Gradient Sign Method (FGSM) and the Carlini-Wagner 𝐿2-norm attack to fool sequence-based deepfake detector models in both the white-box and black-box settings. The experimental results show that the attacks are effective with a maximum success rate of 99.72% and 67.14% in the white-box and black-box attack scenarios, respectively. This highlights the importance of developing more robust sequence-based deepfake detectors and opens up directions for future research.
more »
« less
- Award ID(s):
- 2040209
- PAR ID:
- 10354760
- Date Published:
- Journal Name:
- Proceedings of the 1st Workshop on Security Implications of Deepfakes and Cheapfakes
- Page Range / eLocation ID:
- 13 to 18
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)As machine learning is deployed in more settings, including in security-sensitive applications such as malware detection, the risks posed by adversarial examples that fool machine-learning classifiers have become magnified. Black-box attacks are especially dangerous, as they only require the attacker to have the ability to query the target model and observe the labels it returns, without knowing anything else about the model. Current black-box attacks either have low success rates, require a high number of queries, produce adversarial images that are easily distinguishable from their sources, or are not flexible in controlling the outcome of the attack. In this paper, we present AdversarialPSO, (Code available: https://github.com/rhm6501/AdversarialPSOImages) a black-box attack that uses few queries to create adversarial examples with high success rates. AdversarialPSO is based on Particle Swarm Optimization, a gradient-free evolutionary search algorithm, with special adaptations to make it effective for the black-box setting. It is flexible in balancing the number of queries submitted to the target against the quality of the adversarial examples. We evaluated AdversarialPSO on CIFAR-10, MNIST, and Imagenet, achieving success rates of 94.9%, 98.5%, and 96.9%, respectively, while submitting numbers of queries comparable to prior work. Our results show that black-box attacks can be adapted to favor fewer queries or higher quality adversarial images, while still maintaining high success rates.more » « less
-
We present PROVNINJA, a framework designed to generate adversarial attacks that aim to elude provenance-based Machine Learning (ML) security detectors. PROVNINJA is designed to identify and craft adversarial attack vectors that statistically mimic and impersonate system programs. Leveraging the benign execution profile of system processes commonly observed across a multitude of hosts and networks, our research proposes an efficient and effective method to probe evasive alternatives and devise stealthy attack vectors that are difficult to distinguish from benign system behaviors. PROVNINJA's suggestions for evasive attacks, originally derived in the feature space, are then translated into system actions, leading to the realization of actual evasive attack sequences in the problem space. When evaluated against State-of-The-Art (SOTA) detector models using two realistic Advanced Persistent Threat (APT) scenarios and a large collection of fileless malware samples, PROVNINJA could generate and realize evasive attack variants, reducing the detection rates by up to 59%. We also assessed PROVNINJA under varying assumptions on adversaries' knowledge and capabilities. While PROVNINJA primarily considers the black-box model, we also explored two contrasting threat models that consider blind and white-box attack scenarios.more » « less
-
We present PROVNINJA, a framework designed to generate adversarial attacks that aim to elude provenance-based Machine Learning (ML) security detectors. PROVNINJA is designed to identify and craft adversarial attack vectors that statistically mimic and impersonate system programs. Leveraging the benign execution profile of system processes commonly observed across a multitude of hosts and networks, our research proposes an efficient and effective method to probe evasive alternatives and devise stealthy attack vectors that are difficult to distinguish from benign system behaviors. PROVNINJA's suggestions for evasive attacks, originally derived in the feature space, are then translated into system actions, leading to the realization of actual evasive attack sequences in the problem space. When evaluated against State-of-The-Art (SOTA) detector models using two realistic Advanced Persistent Threat (APT) scenarios and a large collection of fileless malware samples, PROVNINJA could generate and realize evasive attack variants, reducing the detection rates by up to 59%. We also assessed PROVNINJA under varying assumptions on adversaries' knowledge and capabilities. While PROVNINJA primarily considers the black-box model, we also explored two contrasting threat models that consider blind and white-box attack scenarios.more » « less
-
Diffusion models have begun to overshadow GANs and other generative models in industrial applications due to their superior image generation performance. The complex architecture of these models furnishes an extensive array of attack features. In light of this, we aim to design membership inference attacks (MIAs) catered to diffusion models. We first conduct an exhaustive analysis of existing MIAs on diffusion models, taking into account factors such as black-box/white-box models and the selection of attack features. We found that white-box attacks are highly applicable in real-world scenarios, and the most effective attacks presently are white-box. Departing from earlier research, which employs model loss as the attack feature for white-box MIAs, we employ model gradients in our attack, leveraging the fact that these gradients provide a more profound understanding of model responses to various samples. We subject these models to rigorous testing across a range of parameters, including training steps, timestep sampling frequency, diffusion steps, and data variance. Across all experimental settings, our method consistently demonstrated near-flawless attack performance, with attack success rate approaching 100% and attack AUCROC near 1.0. We also evaluated our attack against common defense mechanisms, and observed our attacks continue to exhibit commendable performance.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3494109.3527194
