103 citations · 412 across the 16 of their papers we have counts for
5 papers · 1 filter
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras
We characterize a prevalent weakness of deep neural networks (DNNs)---overthinking---which occurs when a DNN can reach correct predictions before its final layer. Overthinking is c…
Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks
Sanghyun Hong, Michael Davinroy, Yiǧitcan Kaya +5
Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-bo…
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Ali Shafahi, W. Ronny Huang, Mahyar Najibi +4
Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explo…
Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks
Octavian Suciu, Radu Mărginean, Yiğitcan Kaya +2
Recent results suggest that attacks against supervised machine learning systems are quite effective, while defenses are easily bypassed by new attacks. However, the specifications…
Issued for Abuse: Measuring the Underground Trade in Code Signing Certificate
Kristián Kozák, Bum Jun Kwon, Doowon Kim +1
Recent measurements of the Windows code-signing certificate ecosystem have highlighted various forms of abuse that allow malware authors to produce malicious code carrying valid di…