An official website of the United States government
Starting with Gilmer et al. (2018), several works have demonstrated the inevitability of adversarial examples based on different assumptions about the underlying input probability space. It remains unclear, however, whether these results apply to natural image distributions. In this work, we assume the underlying data distribution is captured by some conditional generative model, and prove intrinsic robustness bounds for a general class of classifiers, which solves an open problem in Fawzi et al. (2018). Building upon the state-of-the-art conditional generative models, we study the intrinsic robustness of two common image benchmarks under l2 perturbations, and show the existence of a large gap between the robustness limits implied by our theory and the adversarial robustness achieved by current state-of-the-art robust models.
more »
« less
Improved Estimation of Concentration Under ℓp-Norm Distance Metrics Using Half Spaces
Concentration of measure has been argued to be the fundamental cause of adversarial vulnerability. Mahloujifar et al. (2019) presented an empirical way to measure the concentration of a data distribution using samples, and employed it to find lower bounds on intrinsic robustness for several benchmark datasets. However, it remains unclear whether these lower bounds are tight enough to provide a useful approximation for the intrinsic robustness of a dataset. To gain a deeper understanding of the concentration of measure phenomenon, we first extend the Gaussian Isoperimetric Inequality to non-spherical Gaussian measures and arbitrary ℓp-norms (p ≥ 2). We leverage these theoretical insights to design a method that uses half-spaces to estimate the concentration of any empirical dataset under ℓp-norm distance metrics. Our proposed algorithm is more efficient than Mahloujifar et al. (2019)‘s, and experiments on synthetic datasets and image benchmarks demonstrate that it is able to find much tighter intrinsic robustness bounds. These tighter estimates provide further evidence that rules out intrinsic dataset concentration as a possible explanation for the adversarial vulnerability of state-of-the-art classifiers.
more »
« less
- Award ID(s):
- 1804603
- PAR ID:
- 10281364
- Date Published:
- Journal Name:
- International Conference on Learning Representations (ICLR)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Many recent works have shown that adversarial examples that fool classifiers can be found by minimally perturbing a normal input. Recent theoretical results, starting with Gilmer et al. (2018), show that if the inputs are drawn from a concentrated metric probability space, then adversarial examples with small perturbation are inevitable. A concentrated space has the property that any subset with Ω(1) (e.g., 1/100) measure, according to the imposed distribution, has small distance to almost all (e.g., 99/100) of the points in the space. It is not clear, however, whether these theoretical results apply to actual distributions such as images. This paper presents a method for empirically measuring and bounding the concentration of a concrete dataset which is proven to converge to the actual concentration. We use it to empirically estimate the intrinsic robustness to ℓ∞ and ℓ2 perturbations of several image classification benchmarks.more » « less
-
null (Ed.)We show a hardness result for random smoothing to achieve certified adversarial robustness against attacks in the ℓp ball of radius ϵ when p>2. Although random smoothing has been well understood for the ℓ2 case using the Gaussian distribution, much remains unknown concerning the existence of a noise distribution that works for the case of p>2. This has been posed as an open problem by Cohen et al. (2019) and includes many significant paradigms such as the ℓ∞ threat model. In this work, we show that any noise distribution D over R^d that provides ℓp robustness for all base classifiers with p>2 must satisfy E[η_i^2]= Ω(d^(1−2/p) ϵ^2 (1−δ)/δ^2) for 99% of the features (pixels) of vector η∼D, where ϵ is the robust radius and δ is the score gap between the highest-scored class and the runner-up. Therefore, for high-dimensional images with pixel values bounded in [0,255], the required noise will eventually dominate the useful information in the images, leading to trivial smoothed classifiers.more » « less
-
null (Ed.)We show a hardness result for random smoothing to achieve certified adversarial robustness against attacks in the ℓp ball of radius ϵ when p>2. Although random smoothing has been well understood for the ℓ2 case using the Gaussian distribution, much remains unknown concerning the existence of a noise distribution that works for the case of p>2. This has been posed as an open problem by Cohen et al. (2019) and includes many significant paradigms such as the ℓ∞ threat model. In this work, we show that any noise distribution D over Rd that provides ℓp robustness for all base classifiers with p>2 must satisfy E[η_i^2]=Ω(d^(1−2/p) ϵ^2(1−δ)/δ^2) for 99% of the features (pixels) of vector η∼D, where ϵ is the robust radius and δ is the score gap between the highest-scored class and the runner-up. Therefore, for high-dimensional images with pixel values bounded in [0,255], the required noise will eventually dominate the useful information in the images, leading to trivial smoothed classifiers.more » « less
-
null (Ed.)Randomized smoothing, using just a simple isotropic Gaussian distribution, has been shown to produce good robustness guarantees against ℓ2-norm bounded adversaries. In this work, we show that extending the smoothing technique to defend against other attack models can be challenging, especially in the high-dimensional regime. In particular, for a vast class of i.i.d.~smoothing distributions, we prove that the largest ℓp-radius that can be certified decreases as O(1/d12−1p) with dimension d for p>2. Notably, for p≥2, this dependence on d is no better than that of the ℓp-radius that can be certified using isotropic Gaussian smoothing, essentially putting a matching lower bound on the robustness radius. When restricted to {\it generalized} Gaussian smoothing, these two bounds can be shown to be within a constant factor of each other in an asymptotic sense, establishing that Gaussian smoothing provides the best possible results, up to a constant factor, when p≥2. We present experimental results on CIFAR to validate our theory. For other smoothing distributions, such as, a uniform distribution within an ℓ1 or an ℓ∞-norm ball, we show upper bounds of the form O(1/d) and O(1/d1−1p) respectively, which have an even worse dependence on d.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
