wang2226 / Trojan-Activation-AttackView external linksLinks
[CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.
☆29Jul 29, 2024Updated last year
Alternatives and similar repositories for Trojan-Activation-Attack
Users that are interested in Trojan-Activation-Attack are comparing it to the libraries listed below
Sorting:
- 📜 Paper list on decoding methods for LLMs and LVLMs☆68Nov 7, 2025Updated 3 months ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?"☆21Dec 26, 2025Updated last month
- Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs☆12Nov 7, 2024Updated last year
- Code for the paper "Self-Detoxifying Language Models via Toxification Reversal" (EMNLP 2023)☆18Oct 17, 2023Updated 2 years ago
- Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24…☆26Jun 14, 2024Updated last year
- ☆28Feb 27, 2025Updated 11 months ago
- Backdooring Multimodal Learning☆30May 4, 2023Updated 2 years ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆26Jun 27, 2024Updated last year
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆27Jul 6, 2024Updated last year
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆42Jul 28, 2024Updated last year
- ☆70Feb 16, 2025Updated 11 months ago
- ☆31Jul 14, 2023Updated 2 years ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆31Oct 26, 2023Updated 2 years ago
- ☆37Oct 17, 2024Updated last year
- Official implementation of the WASP web agent security benchmark☆67Aug 12, 2025Updated 6 months ago
- GPG key integration for Blockstack client applications☆10Aug 1, 2017Updated 8 years ago
- [AAMAS 2025] Privacy-preserving and Personalized RLHF, with convergence guarantees. The Code contains experiments for training multiple i…☆14Apr 16, 2025Updated 9 months ago
- Official frontend web application for Moltbook - The Social Network for AI Agents. Built with Next.js 14, TypeScript, Tailwind CSS featur…☆25Feb 1, 2026Updated 2 weeks ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆35Feb 4, 2026Updated last week
- ☆115Jul 2, 2024Updated last year
- Collect and filter location information from social network services.☆11Jun 14, 2020Updated 5 years ago
- Precision Knowledge Editing (PKE): A novel method to reduce toxicity in LLMs while preserving performance, with robust evaluations and ha…☆11Nov 26, 2024Updated last year
- [CVPRW'22] A privacy attack that exploits Adversarial Training models to compromise the privacy of Federated Learning systems.☆11Jul 7, 2022Updated 3 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆109Sep 27, 2024Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆93May 9, 2024Updated last year
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆47Oct 13, 2025Updated 4 months ago
- 🗞 Monitors data sources, alerts you when they change☆13Jul 23, 2021Updated 4 years ago
- FIRE: Combining Multi-Stage Filtering with Taint Analysis for Scalable Recurring Vulnerability Detection.☆15Sep 27, 2024Updated last year
- Using Shodan to get a breakdown of the most common key names in public Redis servers.☆13Dec 10, 2017Updated 8 years ago
- Resources, articles, thoughts, datasets, papers on TI tradecraft☆11Aug 24, 2018Updated 7 years ago
- Normalizer for honeypot data.☆11Dec 6, 2023Updated 2 years ago
- This is the tool released in ICSE 2024 paper "Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Er…☆17Jun 5, 2023Updated 2 years ago
- EmerCoin SSH PKI and distributed ACL☆15Mar 4, 2017Updated 8 years ago
- Proof of concept implementation of a cyber threat intelligence and incident handling platform☆11Feb 10, 2023Updated 3 years ago
- Malware samples observed in the wild from time to time☆12Jul 29, 2019Updated 6 years ago
- CertWatcher is a new take on monitoring for phishing sites. It is meant to be a set and forget service that will send you a daily report …☆10Oct 12, 2020Updated 5 years ago
- HoneyDB Python Module☆14Feb 6, 2024Updated 2 years ago
- Server for managing OpenVPN certificates☆14Aug 18, 2014Updated 11 years ago
- moddwatch watches files and directories for modifications☆18May 23, 2025Updated 8 months ago