Search Results for author:
Found 22 papers, 12 papers with code
A Proactive and Dual Prevention Mechanism against Illegal Song Covers empowered by Singing Voice Conversion
To improve the imperceptibility of perturbations, we refine a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices.
When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code.
SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
Our attack is versatile and can work in both white-box and black-box scenarios.
CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models
Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages.
A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks
Federated learning (FL) is a distributed machine learning (ML) paradigm, allowing multiple clients to collaboratively train shared machine learning (ML) models without exposing clients' data privacy.
An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks
Quantized neural networks (QNNs) have been developed, with binarized neural networks (BNNs) restricted to binary values as a special case.
QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems
Current adversarial attacks against speaker recognition systems (SRSs) require either white-box access or heavy black-box queries to the target SRS, thus still falling behind practical attacks against proprietary commercial APIs and voice-controlled devices.
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.
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
The experimental results show that the proposed estimator helps save 23. 3% of computational cost measured in floating-point operations for the code completion systems, and 80. 2% of rejected prompts lead to unhelpful completion
Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networks
Our approach is orthogonal to and can be integrated with many existing verification techniques.
AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systems
Recent work has illuminated the vulnerability of speaker recognition systems (SRSs) against adversarial attacks, raising significant security concerns in deploying SRSs.
Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition
According to the characteristic of SRSs, we present 22 diverse transformations and thoroughly evaluate them using 7 recent promising adversarial attacks (4 white-box and 3 black-box) on speaker recognition.
CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning
Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community.
SEC4SR: A Security Analysis Platform for Speaker Recognition
To bridge this gap, we present SEC4SR, the first platform enabling researchers to systematically and comprehensively evaluate adversarial attacks and defenses in SR. SEC4SR incorporates 4 white-box and 2 black-box attacks, 24 defenses including our novel feature-level transformations.
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.
BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks
Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications.
Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels
The key insight of our approach is that the robustness verification problem of DNNs can be solved by verifying sub-problems of DNNs, one per target label.
Advanced Evasion Attacks and Mitigations on Practical ML-Based Phishing Website Classifiers
To launch attacks in the white- and grey-box scenarios, we also propose a sample-based collision attack to gain the knowledge of the target classifier.
Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems
In this paper, we conduct the first comprehensive and systematic study of the adversarial attacks on SR systems (SRSs) to understand their security weakness in the practical blackbox setting.
Taking Care of The Discretization Problem: A Comprehensive Study of the Discretization Problem and A Black-Box Adversarial Attack in Discrete Integer Domain
In this work, we first conduct a comprehensive study of existing methods and tools for crafting.
Making Agents' Abilities Explicit
Alternating-time temporal logics (ATL/ATL*) represent a family of modal logics for reasoning about agents' strategic abilities in multiagent systems (MAS).
