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.
☆51Mar 16, 2026Updated 7 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:
- 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 9 months ago
- Repository for 2030 project☆15Dec 29, 2025Updated 10 months ago
- A guard model for Agent☆43Jul 15, 2026Updated 3 months ago
- Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University☆166Jul 10, 2026Updated 3 months ago
- Official code repo for HazardAuditor☆21Sep 20, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆39Jun 13, 2026Updated 4 months ago
- [EMNLP 2026 Findings] HarmProfile: Characterizing Harmful Distributions in Frontier LLMs☆72Aug 26, 2026Updated 2 months ago
- [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆334Sep 8, 2026Updated last month
- ☆31Feb 19, 2025Updated last year
- ShutterMuse, a open-sourced MLLM that provides both photographpher-side and subject-side guidance.☆120Sep 22, 2026Updated last month
- ☆45Sep 29, 2026Updated last month
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆32Nov 2, 2025Updated 11 months ago
- this is for the ACM MM paper---Backdoor Attack on Crowd Counting☆17Jul 10, 2022Updated 4 years ago
- Open-source red teaming framework for MLLMs with 42+ attack methods☆279Jul 17, 2026Updated 3 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic Sys…☆158Oct 21, 2026Updated last week
- ☆36Feb 27, 2025Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆48Feb 3, 2026Updated 8 months ago
- BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models☆16Updated this week
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆41Dec 24, 2023Updated 2 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆118Sep 27, 2024Updated 2 years ago
- “ToolHazard: Scalable Red Teaming of LLM Agents via Adversarial Tool-Interactive Environment and Task Synthesis”☆15Aug 18, 2026Updated 2 months ago
- GUI / Computer-Use / Browser Agent 安全论文清单 —— 按攻防轴组织，每篇附中文简介☆57Oct 21, 2026Updated last week
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆39Oct 29, 2025Updated last year
- [IEEE TDSC] Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks☆16Oct 7, 2025Updated last year
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆38Oct 22, 2026Updated last week
- Official Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆21Jul 1, 2026Updated 3 months ago
- [ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Promp…☆64May 8, 2026Updated 5 months ago
- [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models☆25Oct 7, 2025Updated last year
- Official repository for PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning, accepted at 2025 IEEE Symposium on…☆20Jul 4, 2025Updated last year
- Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety☆296Apr 12, 2026Updated 6 months ago
- [NeurIPS 2024] UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation☆10Jul 5, 2025Updated last year
- 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.
- The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)☆15Jul 18, 2024Updated 2 years ago
- [ICLR2026] Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models☆30Apr 19, 2026Updated 6 months ago
- ☆16Feb 26, 2025Updated last year
- ☆33Mar 4, 2022Updated 4 years ago
- Implement of Implicit Knowledge Extraction Attack.☆25Jul 14, 2026Updated 3 months ago
- OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and …☆257Oct 15, 2026Updated 2 weeks ago
- ☆23Oct 16, 2026Updated last week