Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"
☆37Dec 2, 2025Updated 10 months ago
Alternatives and similar repositories for MEXTRA
Users that are interested in MEXTRA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Memory Injection Attacks on LLM Agents via Query-Only Interaction☆38Aug 11, 2026Updated 2 months ago
- ☆17Jul 2, 2026Updated 3 months ago
- ☆49May 29, 2026Updated 5 months ago
- A simple implementation of DP-RAG☆21Mar 17, 2025Updated last year
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆46Aug 12, 2026Updated 2 months ago
- 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.
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆22Mar 22, 2026Updated 7 months ago
- [EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records☆144Dec 26, 2024Updated last year
- ☆13Jun 7, 2025Updated last year
- RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents☆26Aug 23, 2024Updated 2 years ago
- Train inversion models to synthesize full reasoning traces from reasoning summaries ("bubbles"), then use those synthesized traces to tra…☆24Mar 6, 2026Updated 7 months ago
- [ACL 2026] Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment☆14May 11, 2026Updated 5 months ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆85Mar 25, 2026Updated 7 months ago
- [ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms☆43Jun 4, 2025Updated last year
- ☆22Oct 5, 2026Updated 3 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆53Mar 24, 2026Updated 7 months ago
- [ACL 2024] Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications☆22Apr 9, 2026Updated 6 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆250Oct 23, 2026Updated last week
- Official Implementation of AttnTrace☆15Apr 23, 2026Updated 6 months ago
- ☆28Nov 28, 2023Updated 2 years ago
- Implement of Implicit Knowledge Extraction Attack.☆25Jul 14, 2026Updated 3 months ago
- ☆36Feb 27, 2025Updated last year
- Official implementation of the paper "AWM: Accurate Weight-Matrix Fingerprint for Large Language Models"☆13Feb 20, 2026Updated 8 months ago
- PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents☆32Mar 26, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆51Jun 1, 2026Updated 5 months ago
- [EMNLP2025 Findings] Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction☆11Apr 9, 2026Updated 6 months ago
- ☆19Jun 3, 2026Updated 4 months ago
- [NeurIPS 2025] Official implementation of "GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling"☆15Oct 14, 2025Updated last year
- ☆19Jun 14, 2026Updated 4 months ago
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆102Jun 2, 2026Updated 4 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆83Jun 11, 2026Updated 4 months ago
- ☆16Sep 14, 2026Updated last month
- ☆29Aug 31, 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.
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆51Mar 16, 2026Updated 7 months ago
- ☆13Jul 9, 2024Updated 2 years ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Oct 24, 2024Updated 2 years ago
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆26Sep 16, 2025Updated last year
- ☆39Oct 17, 2024Updated 2 years ago
- Accepted to ACL'25 (main)☆12May 19, 2025Updated last year
- LLM Safeguarding with Internal Representations☆22Apr 27, 2026Updated 6 months ago