Fuzzing: a survey for roadmap
Fuzz testing (fuzzing) has witnessed its prosperity in detecting security flaws recently. It
generates a large number of test cases and monitors the executions for defects. Fuzzing has …
generates a large number of test cases and monitors the executions for defects. Fuzzing has …
Explainable recommendation: A survey and new perspectives
Y Zhang, X Chen - Foundations and Trends® in Information …, 2020 - nowpublishers.com
Explainable recommendation attempts to develop models that generate not only high-quality
recommendations but also intuitive explanations. The explanations may either be post-hoc …
recommendations but also intuitive explanations. The explanations may either be post-hoc …
Are aligned neural networks adversarially aligned?
Large language models are now tuned to align with the goals of their creators, namely to be"
helpful and harmless." These models should respond helpfully to user questions, but refuse …
helpful and harmless." These models should respond helpfully to user questions, but refuse …
Machine learning testing: Survey, landscapes and horizons
This paper provides a comprehensive survey of techniques for testing machine learning
systems; Machine Learning Testing (ML testing) research. It covers 144 papers on testing …
systems; Machine Learning Testing (ML testing) research. It covers 144 papers on testing …
Invisible for both camera and lidar: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks
In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite
various prior studies on its security issues, all of them only consider attacks on camera-or …
various prior studies on its security issues, all of them only consider attacks on camera-or …
Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst
Our goal is to train a policy for autonomous driving via imitation learning that is robust
enough to drive a real vehicle. We find that standard behavior cloning is insufficient for …
enough to drive a real vehicle. We find that standard behavior cloning is insufficient for …
Speech emotion recognition using deep 1D & 2D CNN LSTM networks
We aimed at learning deep emotion features to recognize speech emotion. Two
convolutional neural network and long short-term memory (CNN LSTM) networks, one 1D …
convolutional neural network and long short-term memory (CNN LSTM) networks, one 1D …
An abstract domain for certifying neural networks
We present a novel method for scalable and precise certification of deep neural networks.
The key technical insight behind our approach is a new abstract domain which combines …
The key technical insight behind our approach is a new abstract domain which combines …
Physical attack on monocular depth estimation with optimal adversarial patches
Deep learning has substantially boosted the performance of Monocular Depth Estimation
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …
Ai2: Safety and robustness certification of neural networks with abstract interpretation
We present AI 2, the first sound and scalable analyzer for deep neural networks. Based on
overapproximation, AI 2 can automatically prove safety properties (eg, robustness) of …
overapproximation, AI 2 can automatically prove safety properties (eg, robustness) of …