Search Results for author:
Found 25 papers, 5 papers with code
Verification of Bit-Flip Attacks against Quantized Neural Networks
Recognizing the documented susceptibility of real-valued neural networks to such attacks and the comparative robustness of quantized neural networks (QNNs), in this work, we introduce BFAVerifier, the first verification framework designed to formally verify the absence of bit-flip attacks or to identify all vulnerable parameters in a sound and rigorous manner.
Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
We propose a novel defense strategy, Safety Chain-of-Thought (SCoT), which harnesses the enhanced \textit{reasoning capabilities} of LLMs for proactive assessment of harmful inputs, rather than simply blocking them.
Clustering Properties of Self-Supervised Learning
Self-supervised learning (SSL) methods via joint embedding architectures have proven remarkably effective at capturing semantically rich representations with strong clustering properties, magically in the absence of label supervision.
Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
Instead of directly using responses from partial images for voting, we investigate using them to supervise the LVLM's responses to the original images.
The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap
Finally, we show that unifying these two computation paradigms -- integrating the flexibility and intelligence of LLMs with the rigorous reasoning abilities of FMs -- has transformative potential for the development of trustworthy AI software systems.
Detecting and Explaining Anomalies Caused by Web Tamper Attacks via Building Consistency-based Normality
Web applications are crucial infrastructures in the modern society, which have high demand of reliability and security.
VisionCoder: Empowering Multi-Agent Auto-Programming for Image Processing with Hybrid LLMs
In the field of automated programming, large language models (LLMs) have demonstrated foundational generative capabilities when given detailed task descriptions.
Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation
Federated Unlearning (FU) enables clients to selectively remove the influence of specific data from a trained federated learning model, addressing privacy concerns and regulatory requirements.
LLM-based Abstraction and Concretization for GUI Test Migration
Then, we propose a concretization technique that utilizes the general test logic to guide an LLM in generating the corresponding GUI test case (including events and assertions) for the target app.
Contribution Evaluation of Heterogeneous Participants in Federated Learning via Prototypical Representations
Our core idea is the construction and application of the class contribution momentum indicator from individual, relative, and holistic perspectives, thereby achieving an effective and efficient contribution evaluation of heterogeneous participants without relying on an auxiliary test dataset.
Towards Large Language Model Aided Program Refinement
Moreover, the opaque procedure from specification to code provided by LLM is an uncontrolled black box.
Exploring the Evolution of Hidden Activations with Live-Update Visualization
Monitoring the training of neural networks is essential for identifying potential data anomalies, enabling timely interventions and conserving significant computational resources.
Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography
To further explore the risk in AD systems and the transferability of practical threats, we propose to leverage typographic attacks against AD systems relying on the decision-making capabilities of Vision-LLMs.
PAODING: A High-fidelity Data-free Pruning Toolkit for Debloating Pre-trained Neural Networks
We present PAODING, a toolkit to debloat pretrained neural network models through the lens of data-free pruning.
Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
For those reasons, there is a high demand for trustworthy and rigorous methods to verify the robustness of neural network models.
Supervised Robustness-preserving Data-free Neural Network Pruning
This may be unrealistic in practice, as the data controllers are often reluctant to provide their model consumers with the original data.
A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement
Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs).
DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training
Moreover, our case study shows that our visual solution can well reflect the characteristics of various training scenarios, showing good potential of DVI as a debugging tool for analyzing deep learning training processes.
Repairing Adversarial Texts through Perturbation
Furthermore, such attacks are impossible to eliminate, i. e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training.
Generalizing Neural Networks by Reflecting Deviating Data in Production
However, inputs may deviate from the training dataset distribution in real deployments.
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
In this work, we bridge the gap by proposing a scalable and effective approach for systematically searching for discriminatory samples while extending existing fairness testing approaches to address a more challenging domain, i. e., text classification.
There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
In this work, we conduct an empirical study to evaluate the relationship between coverage, robustness and attack/defense metrics for DNN.
Silas: High Performance, Explainable and Verifiable Machine Learning
This paper introduces a new classification tool named Silas, which is built to provide a more transparent and dependable data analytics service.
GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems
We follow the "verification as planning" paradigm and propose to use model checking techniques to solve planning and goal reasoning problems for autonomous systems.
Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction
In this work, we propose an approach to extract probabilistic automata for interpreting an important class of neural networks, i. e., recurrent neural networks.
