BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step trajectories using unified metrics like ASR and clean accuracy.
☆42Mar 16, 2026Updated 3 months ago
Alternatives and similar repositories for BackdoorAgent
Users that are interested in BackdoorAgent are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University☆158Updated this week
- The evaluation code for A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5☆53Jan 18, 2026Updated 5 months ago
- ☆28Jun 13, 2026Updated last month
- ShutterMuse, a open-sourced MLLM that provides both photographpher-side and subject-side guidance.☆91Jun 25, 2026Updated 2 weeks ago
- [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆316Mar 13, 2026Updated 4 months 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.
- this is for the ACM MM paper---Backdoor Attack on Crowd Counting☆17Jul 10, 2022Updated 4 years ago
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic Sys…☆112Updated this week
- ☆15Feb 26, 2025Updated last year
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆31Jun 24, 2026Updated 2 weeks ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 8 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆71Jun 11, 2026Updated last month
- ☆32Mar 4, 2022Updated 4 years ago
- ☆38Mar 12, 2025Updated last year
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆37Oct 29, 2025Updated 8 months 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.
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆48Feb 3, 2026Updated 5 months ago
- Data-Efficient Backdoor Attacks☆20Jun 15, 2022Updated 4 years ago
- ☆18Jun 15, 2021Updated 5 years ago
- Open-source red teaming framework for MLLMs with 42+ attack methods☆257Mar 25, 2026Updated 3 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆40Dec 24, 2023Updated 2 years ago
- [EMNLP 24] Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models☆19Mar 9, 2025Updated last year
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆62Apr 29, 2026Updated 2 months ago
- [ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining☆21Feb 26, 2025Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆40Oct 3, 2023Updated 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.
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆37Jun 24, 2025Updated last year
- ☆11Jan 25, 2022Updated 4 years ago
- [ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Promp…☆57May 8, 2026Updated 2 months ago
- [ICLR 2025] REFINE: Inversion-Free Backdoor Defense via Model Reprogramming☆13Feb 13, 2025Updated last year
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆29Feb 8, 2021Updated 5 years ago
- Backdooring Multimodal Learning☆30May 4, 2023Updated 3 years ago
- Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety☆274Apr 12, 2026Updated 3 months ago
- Memory Injection Attacks on LLM Agents via Query-Only Interaction☆28Feb 10, 2026Updated 5 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆61Oct 1, 2025Updated 9 months 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.
- [Preprint] Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis☆10Sep 23, 2021Updated 4 years ago
- Pytorch implementation of NPAttack☆12Jul 7, 2020Updated 6 years ago
- ☆27Jan 5, 2026Updated 6 months ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Oct 24, 2024Updated last year
- This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calc…☆12Feb 14, 2023Updated 3 years ago
- code for TPDS paper "Towards Fair and Privacy-Preserving Federated Deep Models"☆32Jun 16, 2022Updated 4 years ago
- ☆64Jun 18, 2026Updated 3 weeks ago