[ICLR'26] Official code for "Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training"
☆17Mar 31, 2026Updated 6 months ago
Alternatives and similar repositories for self-jailbreaking
Users that are interested in self-jailbreaking are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TheMCPCompany: Creating General-purpose Agents with Task-specific Tools☆16Dec 19, 2025Updated 10 months ago
- Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification☆11Nov 15, 2023Updated 2 years ago
- Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks☆10Jul 6, 2021Updated 5 years ago
- Lightweight implementations of generative label models for weakly supervised machine learning☆24Apr 4, 2026Updated 6 months ago
- ☆22Jul 16, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Crosslingual Reasoning through Test-Time Scaling☆22May 13, 2025Updated last year
- Easily run PyTorch on multiple GPUs & machines☆61Aug 4, 2026Updated 2 months ago
- Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.☆50Nov 8, 2024Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆48Feb 3, 2026Updated 8 months ago
- RLCDAlignBench: 44 alignment-failure detection benchmarks and code for 'Just Ask Jev' (RLCD zero-shot detector of AI alignment failures)☆31Sep 25, 2026Updated last month
- ☆35Sep 13, 2023Updated 3 years ago
- ☆68Mar 18, 2026Updated 7 months ago
- AlexNet implementation by Tensorflow.☆20Apr 15, 2023Updated 3 years ago
- ☆47Oct 1, 2026Updated 3 weeks 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.
- Can LLMs generate code-mixed sentences through zero-shot prompting?☆11Apr 18, 2023Updated 3 years ago
- ☆22Oct 25, 2024Updated 2 years ago
- Code to reproduce the experiments in the paper: Does CLIP Bind Concepts? Probing Compositionality in Large Image Models.☆16Oct 14, 2023Updated 3 years ago
- Internalizing steering vectors via fine tuning☆12Sep 6, 2024Updated 2 years ago
- ☆14Oct 6, 2026Updated 3 weeks ago
- A minimal, hackable coding agent harness in Rust☆14Apr 24, 2026Updated 6 months ago
- [TMLR 25] An automated method for explaining complex neuron behaviors in deep vision models using large language models☆12Feb 20, 2025Updated last year
- 🍋 A cross-platform modding library☆18Apr 19, 2026Updated 6 months ago
- [TMLR] Triple Preference Optimization☆31Feb 19, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A clean, fast, and beautiful tool to help you discover the perfect camera prompts for your AI image generation — no more guessing the rig…☆15Dec 4, 2025Updated 10 months ago
- A server scripting API for Sub Rosa.☆14May 18, 2022Updated 4 years ago
- Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.☆13Sep 24, 2026Updated last month
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆11Oct 13, 2026Updated 2 weeks ago
- [ECCV 2024] Characterizing Robustness via Natural Input Gradients☆13Mar 6, 2026Updated 7 months ago
- [NeurIPS 2026 Poster] Flow-based Activation Steering for Inference-Time Intervention.☆20Sep 30, 2026Updated 3 weeks ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆32Nov 2, 2025Updated 11 months ago
- Simple WireGuard interface monitoring☆13Oct 13, 2026Updated 2 weeks ago
- ☆11Nov 9, 2023Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Generate the Tracy-Widom distribution functions for beta = 1, 2, or 4 in Python☆10Mar 15, 2025Updated last year
- Oxford live bumps☆11Jun 5, 2025Updated last year
- Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024☆18Mar 25, 2025Updated last year
- Reviewable capability layer for coding agents: portable skills, workflow patterns, verification gates, token-efficient execution, and bou…☆16Oct 14, 2026Updated 2 weeks ago
- ☆160Jul 7, 2025Updated last year
- Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Expl…☆12Jul 14, 2026Updated 3 months ago
- Generate synthetic labeled data for extremely low-resource languages using bilingual lexicons.☆20Oct 3, 2024Updated 2 years ago