Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechanisms of LLMs, including those developed by Anthropic and other leading AI organizations. Resources
☆19Aug 6, 2024Updated 2 years ago
Alternatives and similar repositories for Many-Shot-Jailbreaking-Demo
Users that are interested in Many-Shot-Jailbreaking-Demo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Mar 30, 2025Updated last year
- GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs☆20Nov 12, 2025Updated 11 months ago
- Official implementation of “Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities”☆11Apr 1, 2026Updated 7 months ago
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆18Apr 3, 2026Updated 7 months ago
- Image Prompt Injection is a demonstrates project about how to embed a malicious prompt within an image using steganography techniques. Th…☆14Aug 7, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ASCII Smuggling Hidden Prompt Injection is a novel approach to hacking AI assistants using Unicode Tags. This project demostrate how to u…☆19Aug 7, 2024Updated 2 years ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated 2 years ago
- Official implementation of "A Casual Perspective for Enhancing Jailbreak Attack and Defense"☆11Oct 16, 2026Updated 3 weeks ago
- ☆27Jan 5, 2026Updated 10 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 2025Updated last year
- Official evaluation toolkit of VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis☆16Nov 27, 2025Updated 11 months ago
- Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples☆11Oct 14, 2024Updated 2 years ago
- Parseltongue is a powerful prompt hacking tool/browser extension for real-time tokenization visualization and seamless text conversion, s…☆20Jan 11, 2025Updated last year
- ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation☆11Dec 23, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code and data for paper "TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights" Accepted by …☆14Apr 16, 2025Updated last year
- Indirect Prompt Injection Methodology (IPIM) - A structured process which security professionals can use to find Indirect Prompt Injectio…☆25Jul 28, 2025Updated last year
- Official implementation of "AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery".☆12Aug 11, 2025Updated last year
- [ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to…☆395Oct 8, 2025Updated last year
- This repository is the replication package of the NeurIPS19 paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"☆12Oct 27, 2019Updated 7 years ago
- Official code repository for the paper "Internal Activation as the Polar Star for Steering Unsafe LLM Behavior"☆16May 31, 2026Updated 5 months ago
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated last year
- ☆66Aug 11, 2024Updated 2 years ago
- ☆25Feb 17, 2026Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- SafeArena is a benchmark for assessing the harmful capabilities of web agents☆27Apr 23, 2025Updated last year
- This repository provides the implementation for studying Sycophancy-Induced Emerging Misalignment (EM) and introduces Gated Finetuning, a…☆17Oct 27, 2026Updated last week
- ☆31May 14, 2025Updated last year
- Project page of G-buffer Objaverse: High-Quality Rendering Dataset of Objaverse.☆12Jul 16, 2024Updated 2 years ago
- The official implementation for "Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space" (AC…☆14Nov 8, 2025Updated last year
- The public repository of ICML 2026 "SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM …☆15May 6, 2026Updated 6 months ago
- This is a Pytorch implementation of contrastive Learning(CL) baselines.☆14Aug 29, 2022Updated 4 years ago
- ☆38Sep 30, 2024Updated 2 years ago
- [ICLR 2025] Codes for AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models☆10Apr 19, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Codex Switch is a VS Code extension that manages multiple Codex accounts and lets you switch between them from the status bar☆19Sep 3, 2026Updated 2 months ago
- ☆17May 15, 2026Updated 5 months ago
- Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency☆16Aug 6, 2025Updated last year
- ☆18Oct 7, 2022Updated 4 years ago
- A collection of some awesome public projects about LLM-based Web Agents and Tools.☆14Apr 25, 2024Updated 2 years ago
- This is the code for StyleGuard☆11Dec 18, 2025Updated 10 months ago
- Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data. NeurIPS'25 Spotlight☆12Jul 30, 2025Updated last year