Publications (21)
-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers
Mahmood Sharif, Lujo Bauer, Michael K. Reiter
This paper proposes a new defense called -ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by clas…
Randomness in ML Defenses Helps Persistent Attackers and Hinders Evaluators
Keane Lucas, Matthew Jagielski, Florian Tramèr +2
It is becoming increasingly imperative to design robust ML defenses. However, recent work has found that many defenses that initially resist state-of-the-art attacks can be broken…
(How) Do people change their passwords after a breach?
Sruti Bhagavatula, Lujo Bauer, Apu Kapadia
To protect against misuse of passwords compromised in a breach, consumers should promptly change affected passwords and any similar passwords on other accounts. Ideally, affected c…
Perry: A High-level Framework for Accelerating Cyber Deception Experimentation
Brian Singer, Yusuf Saquib, Lujo Bauer +1
Cyber deception aims to distract, delay, and detect network attackers with fake assets such as honeypots, decoy credentials, or decoy files. However, today, it is difficult for ope…
Group-based Robustness: A General Framework for Customized Robustness in the Real World
Weiran Lin, Keane Lucas, Neo Eyal +3
Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where t…
A General Framework for Adversarial Examples with Objectives
Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer +1
Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several appli…