ترغب بنشر مسار تعليمي؟ اضغط هنا

Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks

116   0   0.0 ( 0 )
 نشر من قبل Evan Shelhamer
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses against attacks at test time. We propose dynamic defenses, to adapt the model and input during testing, by defensive entropy minimization (dent). Dent alters testing, but not training, for compatibility with existing models and train-time defenses. Dent improves the robustness of adversarially-trained defenses and nominally-trained models against white-box, black-box, and adaptive attacks on CIFAR-10/100 and ImageNet. In particular, dent boosts state-of-the-art defenses by 20+ points absolute against AutoAttack on CIFAR-10 at $epsilon_infty$ = 8/255.



قيم البحث

اقرأ أيضاً

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of underm ining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinforce the structure of a DNN, making its prediction more stable and less likely to be fooled by adversarial samples. We conduct an extensive experimental study proving the efficiency of our method against multiple attacks, comparing it to numerous defenses, both in white-box and black-box setups. Additionally, the implementation of our method brings almost no overhead to the training procedure, while maintaining the prediction performance of the original model on clean samples.
Adversarial examples are perturbed inputs that are designed (from a deep learning networks (DLN) parameter gradients) to mislead the DLN during test time. Intuitively, constraining the dimensionality of inputs or parameters of a network reduces the s pace in which adversarial examples exist. Guided by this intuition, we demonstrate that discretization greatly improves the robustness of DLNs against adversarial attacks. Specifically, discretizing the input space (or allowed pixel levels from 256 values or 8-bit to 4 values or 2-bit) extensively improves the adversarial robustness of DLNs for a substantial range of perturbations for minimal loss in test accuracy. Furthermore, we find that Binary Neural Networks (BNNs) and related variants are intrinsically more robust than their full precision counterparts in adversarial scenarios. Combining input discretization with BNNs furthers the robustness even waiving the need for adversarial training for certain magnitude of perturbation values. We evaluate the effect of discretization on MNIST, CIFAR10, CIFAR100 and Imagenet datasets. Across all datasets, we observe maximal adversarial resistance with 2-bit input discretization that incurs an adversarial accuracy loss of just ~1-2% as compared to clean test accuracy.
The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications. In this paper, we propose a randomized diversification as a defense strategy. We introduce a multi-channel architecture in a gray-box sce nario, which assumes that the architecture of the classifier and the training data set are known to the attacker. The attacker does not only have access to a secret key and to the internal states of the system at the test time. The defender processes an input in multiple channels. Each channel introduces its own randomization in a special transform domain based on a secret key shared between the training and testing stages. Such a transform based randomization with a shared key preserves the gradients in key-defined sub-spaces for the defender but it prevents gradient back propagation and the creation of various bypass systems for the attacker. An additional benefit of multi-channel randomization is the aggregation that fuses soft-outputs from all channels, thus increasing the reliability of the final score. The sharing of a secret key creates an information advantage to the defender. Experimental evaluation demonstrates an increased robustness of the proposed method to a number of known state-of-the-art attacks.
127 - Bin Zhu , Zhaoquan Gu , Le Wang 2021
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection methods usually make assumptions about the adversarial example and attack method (e.g., the word frequency of the adversarial example, the perturbation level of the attack method). However, this limits the applicability of the detection method. To this end, we propose TREATED, a universal adversarial detection method that can defend against attacks of various perturbation levels without making any assumptions. TREATED identifies adversarial examples through a set of well-designed reference models. Extensive experiments on three competitive neural networks and two widely used datasets show that our method achieves better detection performance than baselines. We finally conduct ablation studies to verify the effectiveness of our method.
Machine learning models are typically made available to potential client users via inference APIs. Model extraction attacks occur when a malicious client uses information gleaned from queries to the inference API of a victim model $F_V$ to build a su rrogate model $F_A$ that has comparable functionality. Recent research has shown successful model extraction attacks against image classification, and NLP models. In this paper, we show the first model extraction attack against real-world generative adversarial network (GAN) image translation models. We present a framework for conducting model extraction attacks against image translation models, and show that the adversary can successfully extract functional surrogate models. The adversary is not required to know $F_V$s architecture or any other information about it beyond its intended image translation task, and queries $F_V$s inference interface using data drawn from the same domain as the training data for $F_V$. We evaluate the effectiveness of our attacks using three different instances of two popular categories of image translation: (1) Selfie-to-Anime and (2) Monet-to-Photo (image style transfer), and (3) Super-Resolution (super resolution). Using standard performance metrics for GANs, we show that our attacks are effective in each of the three cases -- the differences between $F_V$ and $F_A$, compared to the target are in the following ranges: Selfie-to-Anime: FID $13.36-68.66$, Monet-to-Photo: FID $3.57-4.40$, and Super-Resolution: SSIM: $0.06-0.08$ and PSNR: $1.43-4.46$. Furthermore, we conducted a large scale (125 participants) user study on Selfie-to-Anime and Monet-to-Photo to show that human perception of the images produced by the victim and surrogate models can be considered equivalent, within an equivalence bound of Cohens $d=0.3$.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا