Search Results for author:
Found 86 papers, 29 papers with code
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models
Generative Large Language Models (LLMs) have made significant strides across various tasks, but they remain vulnerable to backdoor attacks, where specific triggers in the prompt cause the LLM to generate adversary-desired responses.
On-the-fly Synthesis for LTL over Finite Traces: An Efficient Approach that Counts
Existing approaches rely on constructing a complete Deterministic Finite Automaton (DFA) corresponding to the LTLf specification, a process with doubly exponential complexity relative to the formula size in the worst case.
Certified Continual Learning for Neural Network Regression
Our approach is evaluated with multiple neural networks and on two different continual learning methods.
Towards Large Language Model Aided Program Refinement
Moreover, the opaque procedure from specification to code provided by LLM is an uncontrolled black box.
CodeR: Issue Resolving with Multi-Agent and Task Graphs
GitHub issue resolving recently has attracted significant attention from academia and industry.
Ranked #1 on
Bug fixing
on SWE-bench-lite
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications.
ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
Systematic analysis also validates that the generated test scenarios represent meaningful use cases, as well as integrate enhanced measures to probe long-tail risks.
Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning
The application of deep neural network models in various security-critical applications has raised significant security concerns, particularly the risk of backdoor attacks.
How Does Bayes Error Limit Probabilistic Robust Accuracy
This reduced Bayes uncertainty allows a higher upper bound on probabilistic robust accuracy than that on deterministic robust accuracy.
Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors
We first show that the accuracy inevitably decreases in the pursuit of robustness due to changed Bayes error in the altered data distribution.
Evaluating and Mitigating Linguistic Discrimination in Large Language Models
The results show that LLMs exhibit stronger human alignment capabilities with queries in English, French, Russian, and Spanish (only 1. 04\% of harmful queries successfully jailbreak on average) compared to queries in Bengali, Georgian, Nepali and Maithili (27. 7\% of harmful queries jailbreak successfully on average).
Towards General Conceptual Model Editing via Adversarial Representation Engineering
Since the development of Large Language Models (LLMs) has achieved remarkable success, understanding and controlling their internal complex mechanisms has become an urgent problem.
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs).
Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models
This study introduces an innovative method to address event-level hallucinations in MLLMs, focusing on specific temporal understanding in video content.
RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Rates
Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest.
Causality Analysis for Evaluating the Security of Large Language Models
Based on a layer-level causality analysis, we show that RLHF has the effect of overfitting a model to harmful prompts.
Feature Space Renormalization for Semi-supervised Learning
The common framework among recent approaches is to train the model on a large amount of unlabelled data with consistency regularization to constrain the model predictions to be invariant to input perturbation.
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications.
Analyzing and controlling diversity in quantum-behaved particle swarm optimization
Then, the correlations between the two types of diversities and the search performance are tested and analyzed on several benchmark functions, and the distance-to-average-point diversity is showed to have stronger association with the search performance during the evolving processes.
How Generalizable are Deepfake Image Detectors? An Empirical Study
Deepfakes are becoming increasingly credible, posing a significant threat given their potential to facilitate fraud or bypass access control systems.
Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework
The results demonstrate that CFU can improve the classifier on multiple fairness metrics without sacrificing its utility.
Semantic-Based Neural Network Repair
The results show that we are able to repair 100% of a set of randomly generated neural networks (which are produced with an existing AI framework testing approach) effectively and efficiently (with an average repair time of 21. 08s) and 93. 75% of a collection of real neural network bugs (with an average time of 3min 40s).
How Sparse Can We Prune A Deep Network: A Fundamental Limit Viewpoint
In addition, we provide efficient countermeasures to address the challenges in computing the pruning limit, which involves accurate spectrum estimation of a large-scale and non-positive Hessian matrix.
SynGraphy: Succinct Summarisation of Large Networks via Small Synthetic Representative Graphs
In this paper we take the problem of visualising large graphs from a novel perspective: we leave the original graph's nodes and edges behind, and instead summarise its properties such as the clustering coefficient and bipartivity by generating a completely new graph whose structural properties match that of the original graph.
QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks
Experimental results on QNNs with different quantization bits confirm the effectiveness and efficiency of our approach, e. g., two orders of magnitude faster and able to solve more verification tasks in the same time limit than the state-of-the-art methods.
QEBVerif: Quantization Error Bound Verification of Neural Networks
In this work, we propose a quantization error bound verification method, named QEBVerif, where both weights and activation tensors are quantized.
Point Cloud Quality Assessment using 3D Saliency Maps
Considering the importance of saliency detection in quality assessment, we propose an effective full-reference PCQA metric which makes the first attempt to utilize the saliency information to facilitate quality prediction, called point cloud quality assessment using 3D saliency maps (PQSM).
Adaptive Fairness Improvement Based on Causality Analysis
Given a discriminating neural network, the problem of fairness improvement is to systematically reduce discrimination without significantly scarifies its performance (i. e., accuracy).
TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination
The experiment results show that TESTSGDis effective and efficient in identifying and measuring such subtle group discrimination that has never been revealed before.
Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognition
The ultimate goal is to enable a global view that considers the beginning and the end positions to predict the entity.
H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System
We utilize a disparity network to transfer spatiotemporal information across views even in large disparity scenes, based on which, we propose disparity-guided flow-based warping for LSR-HFR view and complementary warping for HSR-LFR view.
Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection
In this way, our model can form a more explicit and discriminative decision boundary to distinguish known and also unseen anomalies from normal samples more effectively.
Ranked #3 on
Supervised Defect Detection
on SensumSODF
Verifying Neural Networks Against Backdoor Attacks
To the best of our knowledge, the only line of work which certifies the absence of backdoor is based on randomized smoothing, which is known to significantly reduce neural network performance.
Causality-based Neural Network Repair
Results also show that thanks to the causality-based fault localization, CARE's repair focuses on the misbehavior and preserves the accuracy of the neural networks.
ExAIS: Executable AI Semantics
In this new paradigm, AI frameworks such as TensorFlow and PyTorch play a key role, which is as essential as the compiler for traditional programs.
Res2NetFuse: A Novel Res2Net-based Fusion Method for Infrared and Visible Images
The encoder based on Res2Net is utilized for extracting multi-scale features from the input image.
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.
No-Reference Point Cloud Quality Assessment via Domain Adaptation
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds.
Ranked #4 on
Point Cloud Quality Assessment
on WPC
Fairness Testing of Deep Image Classification with Adequacy Metrics
DeepFAIT consists of several important components enabling effective fairness testing of deep image classification applications: 1) a neuron selection strategy to identify the fairness-related neurons; 2) a set of multi-granularity adequacy metrics to evaluate the model's fairness; 3) a test selection algorithm for fixing the fairness issues efficiently.
Enhancing Knowledge Tracing via Adversarial Training
The original and adversarial examples are further used to jointly train the KT model, forcing it is not only to be robust to the adversarial examples, but also to enhance the generalization over the original ones.
Probabilistic Verification of Neural Networks Against Group Fairness
Our approach has been evaluated with multiple models trained on benchmark datasets and the experiment results show that our approach is effective and efficient.
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.
Code Integrity Attestation for PLCs using Black Box Neural Network Predictions
Cyber-physical systems (CPSs) are widespread in critical domains, and significant damage can be caused if an attacker is able to modify the code of their programmable logic controllers (PLCs).
Adversarial Attacks and Mitigation for Anomaly Detectors of Cyber-Physical Systems
The threats faced by cyber-physical systems (CPSs) in critical infrastructure have motivated research into a multitude of attack detection mechanisms, including anomaly detectors based on neural network models.
Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection
Consequently, we address the weakness of IoU by introducing one geometric sensitive search algorithm as a new assignment and regression metric.
Attack as Defense: Characterizing Adversarial Examples using Robustness
Though various defense mechanisms have been proposed to improve robustness of deep learning software, many of them are ineffective against adaptive attacks.
MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancy
In this paper, we propose a new distortion quantification method for point clouds, the multiscale potential energy discrepancy (MPED).
Revisiting Classification Perspective on Scene Text Recognition
We demonstrate the effectiveness of the classification perspective on scene text recognition with extensive experiments.
Ranked #6 on
Scene Text Recognition
on ICDAR 2003
RobOT: Robustness-Oriented Testing for Deep Learning Systems
A key part of RobOT is a quantitative measurement on 1) the value of each test case in improving model robustness (often via retraining), and 2) the convergence quality of the model robustness improvement.
Software Engineering
Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
i) We generate a bird view map, which is naturally free from occlusion issues, and scan all points on it to look for suitable locations for each pedestrian instance.
Towards Repairing Neural Networks Correctly
Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication).
Holistic Combination of Structural and Textual Code Information for Context based API Recommendation
APIRec-CST is a deep learning model that combines the API usage with the text information in the source code based on an API Context Graph Network and a Code Token Network that simultaneously learn structural and textual features for API recommendation.
Improving Neural Network Verification through Spurious Region Guided Refinement
The core idea is to make use of the obtained constraints of the abstraction to infer new bounds for the neurons.
SOCRATES: Towards a Unified Platform for Neural Network Analysis
Studies show that neural networks, not unlike traditional programs, are subject to bugs, e. g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness.
Inferring Point Cloud Quality via Graph Similarity
We propose the GraphSIM -- an objective metric to accurately predict the subjective quality of point cloud with superimposed geometry and color impairments.
Active Fuzzing for Testing and Securing Cyber-Physical Systems
Cyber-physical systems (CPSs) in critical infrastructure face a pervasive threat from attackers, motivating research into a variety of countermeasures for securing them.
sFuzz: An Efficient Adaptive Fuzzer for Solidity Smart Contracts
In this work, we present an adaptive fuzzer for smart contracts on the Ethereum platform called sFuzz.
Software Engineering
Learning efficient structured dictionary for image classification
Recent years have witnessed the success of dictionary learning (DL) based approaches in the domain of pattern classification.
Multiplication fusion of sparse and collaborative-competitive representation for image classification
Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively.
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.
Finite-Sample Analysis of Decentralized Temporal-Difference Learning with Linear Function Approximation
Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering applications such as networked robotics, swarming drones, and sensor networks, we investigate the policy evaluation problem in a fully decentralized setting, using temporal-difference (TD) learning with linear function approximation to handle large state spaces in practice.
Understanding Social Networks using Transfer Learning
A detailed understanding of users contributes to the understanding of the Web's evolution, and to the development of Web applications.
A Dual Camera System for High Spatiotemporal Resolution Video Acquisition
This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video.
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.
Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients
The present paper develops a novel aggregated gradient approach for distributed machine learning that adaptively compresses the gradient communication.
Learning from Adversarial Features for Few-Shot Classification
Then we use the adversarial region attention to aggregate the feature maps to obtain the adversarial features.
Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
We further generalize LCCN for open-set noisy labels and the semi-supervised setting.
Ranked #35 on
Image Classification
on Clothing1M
(using extra training data)
Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing
We thus first propose a measure of `sensitivity' and show empirically that normal samples and adversarial samples have distinguishable sensitivity.
Detecting Adversarial Samples for Deep Neural Networks through Mutation Testing
Recently, it has been shown that deep neural networks (DNN) are subject to attacks through adversarial samples.
Learning from Mutants: Using Code Mutation to Learn and Monitor Invariants of a Cyber-Physical System
Cyber-physical systems (CPS) consist of sensors, actuators, and controllers all communicating over a network; if any subset becomes compromised, an attacker could cause significant damage.
Toward `verifying' a Water Treatment System
As the system is too complicated to be manually modeled, we apply latest automatic model learning techniques to construct a set of Markov chains through abstraction and refinement, based on two long system execution logs (one for training and the other for testing).
Deep Learning from Noisy Image Labels with Quality Embedding
However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches.
Anomaly Detection for a Water Treatment System Using Unsupervised Machine Learning
In this paper, we propose and evaluate the application of unsupervised machine learning to anomaly detection for a Cyber-Physical System (CPS).
On Study of the Reliable Fully Convolutional Networks with Tree Arranged Outputs (TAO-FCN) for Handwritten String Recognition
The handwritten string recognition is still a challengeable task, though the powerful deep learning tools were introduced.
Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition
We design a nine-layer CNN for HCCR consisting of 3, 755 classes, and devise an algorithm that can reduce the networks computational cost by nine times and compress the network to 1/18 of the original size of the baseline model, with only a 0. 21% drop in accuracy.
An Automated CNN Recommendation System for Image Classification Tasks
In order to solve this problem, we proposed an automated CNN recommendation system for image classification task.
Predicting User Roles in Social Networks using Transfer Learning with Feature Transformation
How can we recognise social roles of people, given a completely unlabelled social network?
Automatically 'Verifying' Discrete-Time Complex Systems through Learning, Abstraction and Refinement
The other is a probabilistic model based on which the given property is `verified'.
Software Engineering
Towards Learning and Verifying Invariants of Cyber-Physical Systems by Code Mutation
Cyber-physical systems (CPS), which integrate algorithmic control with physical processes, often consist of physically distributed components communicating over a network.
A Novel Scene Text Detection Algorithm Based On Convolutional Neural Network
In this paper, we propose a CNN based scene text detection algorithm with a new text region extractor.
A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine
The proposed Chinese text recognition algorithm is evaluated with two Chinese text datasets.
On Study of the Binarized Deep Neural Network for Image Classification
Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network.
A Feature-based Classification Technique for Answering Multi-choice World History Questions
Our FRDC_QA team participated in the QA-Lab English subtask of the NTCIR-11.
Random Drift Particle Swarm Optimization
The free electron model considers that electrons have both a thermal and a drift motion in a conductor that is placed in an external electric field.
