Search Results for author:
Found 19 papers, 15 papers with code
Causal Transportability for Visual Recognition
Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features.
A Tale of Two Models: Constructing Evasive Attacks on Edge Models
In this paper, we introduce a new evasive attack, DIVA, that exploits these differences in edge adaptation, by adding adversarial noise to input data that maximizes the output difference between the original and adapted model.
Using Multiple Self-Supervised Tasks Improves Model Robustness
In this paper, we propose a novel defense that can dynamically adapt the input using the intrinsic structure from multiple self-supervised tasks.
Adversarial Attacks are Reversible with Natural Supervision
We find that images contain intrinsic structure that enables the reversal of many adversarial attacks.
BPF for storage: an exokernel-inspired approach
The overhead of the kernel storage path accounts for half of the access latency for new NVMe storage devices.
Operating Systems Databases
Generative Interventions for Causal Learning
We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts.
Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity
We thus train the model to learn execution semantics from the functions' micro-traces, without any manual labeling effort.
What Does CNN Shift Invariance Look Like? A Visualization Study
We present the results of three experiments comparing representations of millions of images with exhaustively shifted objects, examining both local invariance (within a few pixels) and global invariance (across the image frame).
XDA: Accurate, Robust Disassembly with Transfer Learning
We present XDA, a transfer-learning-based disassembly framework that learns different contextual dependencies present in machine code and transfers this knowledge for accurate and robust disassembly.
Multitask Learning Strengthens Adversarial Robustness
Although deep networks achieve strong accuracy on a range of computer vision benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input perturbations fool the network.
Live Trojan Attacks on Deep Neural Networks
We propose a live attack on deep learning systems that patches model parameters in memory to achieve predefined malicious behavior on a certain set of inputs.
AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
Due to the inherent robustness of segmentation models, traditional norm-bounded attack methods show limited effect on such type of models.
Metric Learning for Adversarial Robustness
Deep networks are well-known to be fragile to adversarial attacks.
Efficient Formal Safety Analysis of Neural Networks
Our approach can check different safety properties and find concrete counterexamples for networks that are 10$\times$ larger than the ones supported by existing analysis techniques.
NEUZZ: Efficient Fuzzing with Neural Program Smoothing
However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs.
Formal Security Analysis of Neural Networks using Symbolic Intervals
In this paper, we present a new direction for formally checking security properties of DNNs without using SMT solvers.
Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems
Finally, we show that retraining using the safety violations detected by VeriVis can reduce the average number of violations up to 60. 2%.
PanNet: A Deep Network Architecture for Pan-Sharpening
We incorporate domain-specific knowledge to design our PanNet architecture by focusing on the two aims of the pan-sharpening problem: spectral and spatial preservation.
DeepXplore: Automated Whitebox Testing of Deep Learning Systems
First, we introduce neuron coverage for systematically measuring the parts of a DL system exercised by test inputs.
