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.
☆44Mar 16, 2026Updated 4 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 6 months ago
- Repository for 2030 project☆15Dec 29, 2025Updated 7 months ago
- A guard model for Agent☆40Jul 15, 2026Updated 2 weeks ago
- Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University☆159Jul 10, 2026Updated 3 weeks ago
- ☆30Jun 13, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ShutterMuse, a open-sourced MLLM that provides both photographpher-side and subject-side guidance.☆95Jun 25, 2026Updated last month
- ☆30Feb 19, 2025Updated last year
- [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆322Mar 13, 2026Updated 4 months ago
- Open-source red teaming framework for MLLMs with 42+ attack methods☆259Jul 17, 2026Updated 2 weeks ago
- 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…☆121Updated this week
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆48Feb 3, 2026Updated 6 months ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 9 months ago
- ☆33Feb 27, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆34Jun 24, 2026Updated last month
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆116Sep 27, 2024Updated last year
- [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models☆25Oct 7, 2025Updated 9 months ago
- Official repository for PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning, accepted at 2025 IEEE Symposium on…☆18Jul 4, 2025Updated last year
- Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety☆275Apr 12, 2026Updated 3 months ago
- ☆15Feb 26, 2025Updated last year
- [ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining☆23Feb 26, 2025Updated last year
- Implement of Implicit Knowledge Extraction Attack.☆24Jul 14, 2026Updated 3 weeks ago
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆75May 8, 2026Updated 2 months 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.
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆20Mar 22, 2026Updated 4 months ago
- ☆32Mar 4, 2022Updated 4 years ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆37Oct 29, 2025Updated 9 months ago
- Official Implementation of "Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation" and …☆21Dec 24, 2025Updated 7 months ago
- ☆18Jun 15, 2021Updated 5 years ago
- Data-Efficient Backdoor Attacks☆20Jun 15, 2022Updated 4 years ago
- ☆22Dec 18, 2025Updated 7 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆40Dec 24, 2023Updated 2 years ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆17Jun 2, 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.
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆18Jul 1, 2026Updated last month
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆75Jun 11, 2026Updated last month
- This is an official code repository for CVPR 2025 paper BadVision.☆16Nov 18, 2025Updated 8 months ago
- ☆18Apr 1, 2025Updated last year
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆30Updated this week
- RAB: Provable Robustness Against Backdoor Attacks☆40Oct 3, 2023Updated 2 years ago
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆18Jun 24, 2026Updated last month