A
Anish Athalye
Researcher at Massachusetts Institute of Technology
Publications - 17
Citations - 5375
Anish Athalye is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Threat model & Robustness (computer science). The author has an hindex of 12, co-authored 16 publications receiving 4258 citations.
Papers
More filters
Posted Content
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
TL;DR: This work identifies obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples, and develops attack techniques to overcome this effect.
Proceedings Article
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
TL;DR: In this article, the authors identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples.
Posted Content
On Evaluating Adversarial Robustness
Nicholas Carlini,Anish Athalye,Nicolas Papernot,Wieland Brendel,Jonas Rauber,Dimitris Tsipras,Ian Goodfellow,Aleksander Madry,Alexey Kurakin +8 more
TL;DR: The methodological foundations are discussed, commonly accepted best practices are reviewed, and new methods for evaluating defenses to adversarial examples are suggested.
Proceedings Article
Synthesizing Robust Adversarial Examples
TL;DR: In this paper, the authors demonstrate the existence of robust 3D adversarial objects, and present the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations, synthesizing two-dimensional adversarial images that are robust to noise, distortion, and affine transformation.
Posted Content
Synthesizing Robust Adversarial Examples
TL;DR: The existence of robust 3D adversarial objects is demonstrated, and the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations is presented, which synthesizes two-dimensional adversarial images that are robust to noise, distortion, and affine transformation.