Alternatives and similar repositories for PrivAgent:

Users that are interested in PrivAgent are comparing it to the libraries listed below

• SORRY-Bench / sorry-bench
  SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
  ☆43Updated 7 months ago
• lancopku / agent-backdoor-attacks
  Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]
  ☆60Updated 4 months ago
• reds-lab / BEEAR
  This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…
  ☆14Updated 7 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆55Updated last month
• lapisrocks / rpo
  Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"
  ☆49Updated 6 months ago
• rotaryhammer / code-autodan
  An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
  ☆35Updated last year
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆22Updated last year
• SheltonLiu-N / Universal-Prompt-Injection
  The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".
  ☆40Updated 3 months ago
• AI45Lab / ActorAttack
  ☆74Updated 2 weeks ago
• pasquini-dario / LLM_NeuralExec
  Code to generate NeuralExecs (prompt injection for LLMs)
  ☆19Updated 2 months ago
• swj0419 / muse_bench
  ☆20Updated 7 months ago
• kztakemoto / simbaja
  All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
  ☆16Updated 9 months ago
• AI45Lab / CodeAttack
  [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
  ☆36Updated 3 months ago
• BHui97 / PLeak
  ☆50Updated 2 months ago
• AI-secure / RedCode
  [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  ☆26Updated last month
• AI-secure / AgentPoison
  [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
  ☆91Updated 3 weeks ago
• EddyLuo1232 / JailBreakV_28K
  [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…
  ☆46Updated 7 months ago
• yuplin2333 / representation-space-jailbreak
  Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…
  ☆19Updated 6 months ago
• uiuc-kang-lab / InjecAgent
  ☆51Updated 7 months ago
• Django-Jiang / BadChain
  [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
  ☆26Updated 6 months ago
• wang2226 / Trojan-Activation-Attack
  [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.
  ☆20Updated 6 months ago
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆47Updated 4 months ago
• Lyz1213 / BadEdit
  ☆22Updated 4 months ago
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆49Updated 6 months ago
• CLAS2024 / starter-kit
  ☆36Updated 3 months ago
• Confirm-Solutions / flrt
  Fluent student-teacher redteaming
  ☆19Updated 6 months ago
• NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
  ☆31Updated 8 months ago
• ThuCCSLab / JailbreakEval
  [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆110Updated this week
• OPTML-Group / SOUL
  Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"
  ☆17Updated 4 months ago
• Sizhe-Chen / StruQ
  official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries
  ☆27Updated 2 months ago