[CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.
β29Jul 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:
- π Paper list on decoding methods for LLMs and LVLMsβ70Nov 7, 2025Updated 4 months ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?"β21Dec 26, 2025Updated 2 months ago
- Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24β¦β26Jun 14, 2024Updated last year
- β29Feb 27, 2025Updated last year
- β58Jun 13, 2024Updated last year
- β71Feb 16, 2025Updated last year
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"β31Oct 26, 2023Updated 2 years ago
- β31Jul 14, 2023Updated 2 years ago
- Official implementation of the WASP web agent security benchmarkβ71Aug 12, 2025Updated 6 months ago
- MCPify all the projects!β27Nov 28, 2025Updated 3 months ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agenβ¦β39Feb 14, 2026Updated 3 weeks ago
- [AAMAS 2025] Privacy-preserving and Personalized RLHF, with convergence guarantees. The Code contains experiments for training multiple iβ¦β15Apr 16, 2025Updated 10 months ago
- GPG key integration for Blockstack client applicationsβ10Aug 1, 2017Updated 8 years ago
- β11Sep 6, 2024Updated last year
- [CVPRW'22] A privacy attack that exploits Adversarial Training models to compromise the privacy of Federated Learning systems.β12Jul 7, 2022Updated 3 years ago
- Precision Knowledge Editing (PKE): A novel method to reduce toxicity in LLMs while preserving performance, with robust evaluations and haβ¦β11Nov 26, 2024Updated last year
- β118Jul 2, 2024Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]β109Sep 27, 2024Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.β93May 9, 2024Updated last year
- β20Feb 3, 2025Updated last year
- Proof of concept implementation of a cyber threat intelligence and incident handling platformβ11Feb 10, 2023Updated 3 years ago
- π Monitors data sources, alerts you when they changeβ13Jul 23, 2021Updated 4 years ago
- β12Nov 19, 2025Updated 3 months ago
- Application which generates the structure and related files necessary for developing a Data Exchange Layer (DXL) integration with Pythonβ12Mar 17, 2020Updated 5 years ago
- Blackcert monitors Certificate Transparency Logs for a keyword. Blackcert collects any certificate changes for this keyword and also checβ¦β10Dec 8, 2022Updated 3 years ago
- This is the tool released in ICSE 2024 paper "Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Erβ¦β17Jun 5, 2023Updated 2 years ago
- Using Shodan to get a breakdown of the most common key names in public Redis servers.β13Dec 10, 2017Updated 8 years ago
- β16May 16, 2025Updated 9 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"β47Oct 13, 2025Updated 4 months ago
- moddwatch watches files and directories for modificationsβ18May 23, 2025Updated 9 months ago
- Github Repo for ICML 2022 paper: Communication-Efficient Adaptive Federated Learningβ10Nov 18, 2022Updated 3 years ago
- Resources, articles, thoughts, datasets, papers on TI tradecraftβ11Aug 24, 2018Updated 7 years ago
- Server for managing OpenVPN certificatesβ14Aug 18, 2014Updated 11 years ago
- [DEPRECATED] You should use web3.py instead.β10Nov 24, 2016Updated 9 years ago
- Set up Privoxy as a HTTP proxy that can redirect traffic via the I2P or Tor networksβ13Jun 23, 2025Updated 8 months ago
- Malware samples observed in the wild from time to timeβ12Jul 29, 2019Updated 6 years ago
- β53May 24, 2023Updated 2 years ago
- β48May 9, 2024Updated last year
- β15Sep 24, 2024Updated last year