Official implementation of Visco-Attack (EMNLP 2025 Main). We will progressively release the code and one-click reproduction scripts.
☆30Aug 22, 2025Updated 7 months ago
Alternatives and similar repositories for Visco-Attack
Users that are interested in Visco-Attack are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of “Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models” (AAAI 2026).☆33Dec 17, 2025Updated 3 months ago
- Diagnostic Framework for LLMs and MLLMs☆35Mar 2, 2026Updated 3 weeks ago
- Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models☆31Oct 6, 2025Updated 5 months ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆57Jul 21, 2025Updated 8 months ago
- ☆30May 22, 2024Updated last year
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"☆28Dec 6, 2024Updated last year
- The repository of the paper "REEF: Representation Encoding Fingerprints for Large Language Models," aims to protect the IP of open-source…☆75Jan 16, 2025Updated last year
- ☆11Oct 25, 2024Updated last year
- Code implementation for paper "Can Large Language Models Empower Molecular Property Prediction?"☆39Jul 14, 2023Updated 2 years ago
- Official repository of Siggraph Asia 2025 paper "LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representa…☆26Dec 24, 2025Updated 3 months ago
- Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechan…☆16Aug 6, 2024Updated last year
- ☆14Apr 6, 2025Updated 11 months ago
- ☆16Oct 18, 2023Updated 2 years ago
- 北京邮电大学生存指南，从沙河到本部，从入学到毕业的全程陪伴☆36Mar 17, 2026Updated last week
- 🌿快速生成文件夹目录结构，支持定义目录层级，支持生成到 markdown 文件。☆13Oct 19, 2022Updated 3 years ago
- Chinese-native image generation while compatible with SD eco-system, 1st-gen, AAAI2025☆13Jun 25, 2024Updated last year
- Code of paper "AdvReverb: AdvReverb: Rethinking the Stealthiness of Audio Adversarial Examples to Human Perception"☆19Nov 26, 2023Updated 2 years ago
- The reinforcement learning codes for dataset SPA-VL☆45Jun 24, 2024Updated last year
- A lifecycle guard skill.☆73Updated this week
- 【ACL 2024】 SALAD benchmark & MD-Judge☆171Mar 8, 2025Updated last year
- ☆28Jul 16, 2024Updated last year
- The official code of our CVPR 2024 paper, "3D Human Pose Perception from Egocentric Stereo Videos".☆25Dec 12, 2025Updated 3 months ago
- zotero-pdf2zh 的 Homebrew 安装脚本，让你可以轻松在本地部署 Zotero PDF 翻译服务器☆44Mar 5, 2026Updated 2 weeks ago
- ☆24Mar 9, 2025Updated last year
- ☆11Mar 24, 2023Updated 2 years ago
- A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository agg…☆194Mar 4, 2026Updated 2 weeks ago
- 🧨 TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?☆74Nov 27, 2025Updated 3 months ago
- ☆12Jan 25, 2025Updated last year
- Confidence Regulation Neurons in Language Models (NeurIPS 2024)☆15Feb 1, 2025Updated last year
- ☆55Dec 7, 2024Updated last year
- Official code for PLoP☆17Mar 6, 2026Updated 2 weeks ago
- REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective☆21Feb 28, 2025Updated last year
- Linux进程间通信（消息队列/信号量+共享内存）☆19Jun 8, 2018Updated 7 years ago
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆17Jul 11, 2025Updated 8 months ago
- 🔥🔥🔥Latest Papers, Codes on Uncertainty-based RL☆59Aug 24, 2025Updated 7 months ago
- [CVPR2025] T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation☆33Jul 10, 2025Updated 8 months ago
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated 9 months ago
- Code and full version of the paper "Hijacking Attacks against Neural Network by Analyzing Training Data"☆14Feb 28, 2024Updated 2 years ago
- ☆13Oct 21, 2021Updated 4 years ago