Memory Injection Attacks on LLM Agents via Query-Only Interaction
☆37Aug 11, 2026Updated last month
Alternatives and similar repositories for MINJA
Users that are interested in MINJA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆23Sep 2, 2026Updated last week
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆38Dec 2, 2025Updated 9 months ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆61Jul 16, 2026Updated last month
- Code for paper "Membership Inference Attacks Against Vision-Language Models"☆32Jan 25, 2025Updated last year
- ☆16Jul 2, 2026Updated 2 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.
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆243Aug 16, 2026Updated 3 weeks ago
- ☆44Mar 24, 2026Updated 5 months ago
- Adversaial attack comparative assessment Large Language Model☆13May 21, 2025Updated last year
- ☆18Apr 1, 2025Updated last year
- [VLM-Attack-Survey-2024] Paper list and projects for VLM attacks☆17Feb 12, 2025Updated last year
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆95Jun 2, 2026Updated 3 months ago
- [ACL'26 Main Oral] Official code for "LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation".☆44Aug 25, 2026Updated 2 weeks ago
- ☆14Updated this week
- ☆35Apr 22, 2025Updated last year
- 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.
- Code base for LLM Unlearning via Neural Activation Redirection (NeurIPS 2025).☆21Nov 19, 2025Updated 9 months ago
- An end-to-end security evaluation framework tailored for real-world personalized agent.☆15Feb 28, 2026Updated 6 months ago
- Agent Security Bench (ASB)☆297Apr 16, 2026Updated 4 months ago
- Code associated with ICML (2024). "Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normaliz…☆11Feb 22, 2026Updated 6 months ago
- ☆15Feb 11, 2025Updated last year
- ☆49Dec 9, 2025Updated 9 months ago
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆46Mar 16, 2026Updated 5 months ago
- DICE: Detecting In-distribution Data Contamination with LLM's Internal State☆11Sep 21, 2024Updated last year
- Demo code for the paper: One Thing to Fool them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features☆12Nov 30, 2023Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆12Sep 8, 2023Updated 3 years ago
- [CVPR 2026] SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution☆18Jul 22, 2026Updated last month
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆44Aug 12, 2026Updated last month
- In this project, we used 3 different metrics (Information Gain, Mutual Information, Chi Squared) to find important words and then we used…☆11Aug 7, 2018Updated 8 years ago
- The official code for ``An Engorgio Prompt Makes Large Language Model Babble on''☆24Aug 9, 2025Updated last year
- ☆45May 29, 2026Updated 3 months ago
- Continuous Bag-of-Words (CBOW model implemented in pytorch☆14Feb 27, 2018Updated 8 years ago
- A new benchmark of 118 ICPC problems for evaluating LLM reasoning in competitive coding, featuring realistic ICPC competition scenario, r…☆18May 18, 2025Updated last year
- ☆102Mar 20, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆197Oct 31, 2025Updated 10 months ago
- this is for the ACM MM paper---Backdoor Attack on Crowd Counting☆17Jul 10, 2022Updated 4 years ago
- Cache Me, Catch You: Cache Related Security Threats in LLM Serving Frameworks (NDSS 2026)☆19Dec 18, 2025Updated 8 months ago
- ☆11Apr 6, 2019Updated 7 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆818Jun 2, 2026Updated 3 months ago
- The official implementation for "Mitigating Overthinking in Large Reasoning Models via Manifold Steering"☆15May 29, 2025Updated last year
- The official implementation of the paper "AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?"☆79May 19, 2026Updated 3 months ago