Search Results for author:
Found 11 papers, 3 papers with code
Mechanistically Interpreting a Transformer-based 2-SAT Solver: An Axiomatic Approach
Inspired by the notion of abstract interpretation from the program analysis literature that aims to develop approximate semantics for programs, we give a set of axioms that formally characterize a mechanistic interpretation as a description that approximately captures the semantics of the neural network under analysis in a compositional manner.
Concept-based Analysis of Neural Networks via Vision-Language Models
The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures.
Transfer Attacks and Defenses for Large Language Models on Coding Tasks
They improve upon previous neural network models of code, such as code2seq or seq2seq, that already demonstrated competitive results when performing tasks such as code summarization and identifying code vulnerabilities.
Is Certifying $\ell_p$ Robustness Still Worthwhile?
There are three layers to this inquiry, which we address in this paper: (1) why do we care about robustness research?
Assumption Generation for the Verification of Learning-Enabled Autonomous Systems
Our insight is that we can analyze the system in the absence of the DNN perception components by automatically synthesizing assumptions on the DNN behaviour that guarantee the satisfaction of the required safety properties.
Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study
We address the above challenges by replacing the camera and the network with a compact probabilistic abstraction built from the confusion matrices computed for the DNN on a representative image data set.
On the Perils of Cascading Robust Classifiers
We present \emph{cascade attack} (CasA), an adversarial attack against cascading ensembles, and show that: (1) there exists an adversarial input for up to 88\% of the samples where the ensemble claims to be certifiably robust and accurate; and (2) the accuracy of a cascading ensemble under our attack is as low as 11\% when it claims to be certifiably robust and accurate on 97\% of the test set.
Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components
We use the method in simulation to synthesise controllers for mobile-robot collision mitigation and for maintaining driver attentiveness in shared-control autonomous driving.
Degradation Attacks on Certifiably Robust Neural Networks
Certifiably robust neural networks employ provable run-time defenses against adversarial examples by checking if the model is locally robust at the input under evaluation.
Self-Correcting Neural Networks For Safe Classification
These constraints relate requirements on the order of the classes output by a classifier to conditions on its input, and are expressive enough to encode various interesting examples of classifier safety specifications from the literature.
Robustness of Neural Networks: A Probabilistic and Practical Approach
Our algorithm uses abstract interpretation to approximate the behavior of a neural network and compute an overapproximation of the input regions that violate robustness.
