Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks11 from public data
- A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment139
This paper introduces the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization, and represents the first safety survey to encompass the entire lifecycle of LLMs.
- Malsight: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization15
This work proposes Malsight, a novel code summarization framework that can iteratively generate descriptions of binary malware by exploring malicious source code and benign pseudocode and proposes a novel evaluation benchmark, BLEURT-sum, to measure the quality of summaries.
- Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems9
Comprehensive evaluation on four commercial ASR APIs demonstrates the protection superiority of AudioShield over existing competitors, and both objective and subjective evaluations indicate that AudioShield significantly improves the audio quality.
- Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer8
Experimental results show that the proposed attack on ASR systems based on user-customized style transfer can meet the need for user-customized styles and achieve a success rate of 82% in attacks, while keeping sound naturalness due to the authors' user study.
- Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization4
This work proposes a technique called Acoustic Representation Optimization that aligns adversarial perturbations with low-level acoustic characteristics derived from speech representation models to enhance the cross-model transferability of adversarial examples without degrading audio quality.
- CleanBase: Detecting Malicious Documents in RAG Knowledge Databases1
Experimental results across multiple datasets and prompt injection attacks demonstrate that CleanBase accurately detects malicious documents and effectively safeguards RAG systems.
- DUAP: Dual-task Universal Adversarial Perturbations Against Voice Control Systems–
This work proposes Dual-task Universal Adversarial Perturbation (DUAP), which employs a targeted surrogate objective to effectively disrupt ASR transcription and introduces a Dynamic Normalized Ensemble (DNE) strategy to enhance transferability across diverse SR models.
- –
- –
- Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems–
This work proposes the Mirage and Mute Attack (M2A) framework, which is designed for targeted adversarial attacks on polyphonic SED systems, and introduces a novel evaluation metric Editing Precison that balances effectiveness and precision.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.