• Publications
  • Influence
Towards Evaluating the Robustness of Neural Networks
TLDR
It is demonstrated that defensive distillation does not significantly increase the robustness of neural networks, and three new attack algorithms are introduced that are successful on both distilled and undistilled neural networks with 100% probability are introduced.
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
TLDR
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.
Practical techniques for searches on encrypted data
TLDR
This work describes the cryptographic schemes for the problem of searching on encrypted data and provides proofs of security for the resulting crypto systems, and presents simple, fast, and practical algorithms that are practical to use today.
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
TLDR
It is concluded that adversarialExamples are significantly harder to detect than previously appreciated, and the properties believed to be intrinsic to adversarial examples are in fact not.
TinySec: a link layer security architecture for wireless sensor networks
TLDR
TinySec is introduced, the first fully-implemented link layer security architecture for wireless sensor networks, and results on a 36 node distributed sensor network application clearly demonstrate that software based link layer protocols are feasible and efficient, adding less than 10% energy, latency, and bandwidth overhead.
Android permissions demystified
TLDR
Stowaway, a tool that detects overprivilege in compiled Android applications, is built and finds that about one-third of applications are overprivileged.
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
TLDR
A white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end has a 100% success rate, and the feasibility of this attack introduce a new domain to study adversarial examples.
Private Circuits: Securing Hardware against Probing Attacks
TLDR
This paper proposes several efficient techniques for building private circuits resisting side channel attacks, and provides a formal threat model and proofs of security for their constructions.
Intercepting mobile communications: the insecurity of 802.11
TLDR
Several serious security flaws in the Wired Equivalent Privacy protocol are discovered, stemming from mis-application of cryptographic primitives, which lead to a number of practical attacks that demonstrate that WEP fails to achieve its security goals.
Analyzing inter-application communication in Android
TLDR
This work examines Android application interaction and identifies security risks in application components and provides a tool, ComDroid, that detects application communication vulnerabilities and found 34 exploitable vulnerabilities.
...
1
2
3
4
5
...