[USENIX Security 2025] Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models
☆19Jun 21, 2025Updated last year
Alternatives and similar repositories for Topic-FlipRAG
Users that are interested in Topic-FlipRAG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆25Jan 6, 2025Updated last year
- Imitation Adversarial Attacks for Black-box Neural Ranking Models☆13Feb 5, 2024Updated 2 years ago
- [AAAI 2026] Official implementation of "Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems".☆21Mar 23, 2026Updated 7 months ago
- Evaluation-Driven Development for OpenClaw agents — mine golden cases from real sessions, catch regressions before they ship.☆18Mar 17, 2026Updated 7 months ago
- ☆34Sep 15, 2024Updated 2 years 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.
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆306Jan 27, 2026Updated 9 months ago
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆51Dec 14, 2023Updated 2 years ago
- Official Implementation of "Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation" and …☆21Dec 24, 2025Updated 10 months ago
- ☆65Mar 11, 2025Updated last year
- Official implementation for the NeurIPS 2025 paper: "FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Langua…☆20Apr 25, 2026Updated 6 months ago
- ☆21Jan 15, 2024Updated 2 years ago
- Code for "Backdoor Attacks on Dense Passage Retrievers for Disseminating Misinformation"☆10Nov 11, 2025Updated 11 months ago
- HARMONIC: harnessing LLMs for tabular data synthesis and privacy protection (arXiv:2408.02927)☆13Oct 8, 2026Updated 3 weeks ago
- ☆20Feb 11, 2024Updated 2 years 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.
- SEO attack on dense embedding-based retrieval via poisoning☆15Dec 6, 2025Updated 10 months ago
- [EMNLP'26 Main] SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation☆15Aug 25, 2026Updated 2 months ago
- Code for "TrustRAG: Enhancing Robustness and Trustworthiness in RAG" AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)☆62Mar 24, 2025Updated last year
- ☆11Dec 23, 2024Updated last year
- ☆12Jan 30, 2023Updated 3 years ago
- Claude Code skill for writing security/privacy/cryptography papers. Derived from Orchestra-Research/AI-Research-SKILLs (MIT); composabl…☆21Jun 1, 2026Updated 4 months ago
- ☆12Jul 25, 2025Updated last year
- Official code for "TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization", CVPR 2023☆13Apr 26, 2023Updated 3 years ago
- The code and data of SIGIR21 paper "Package Recommendation with Intra- and Inter-Package Attention Networks".☆12Jun 23, 2021Updated 5 years 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.
- For making notes when researching and studying.☆10Jul 29, 2022Updated 4 years ago
- 简历生成 Skill（Codex / Claude Code/OpenCode 等）：以 Markdown 为内容源，多套可切换模板、多配色、可选证件照，WeasyPrint 离线渲染为可搜索 A4 PDF；内置 STAR/量化润色与 JD 定向匹配。☆49Jul 19, 2026Updated 3 months ago
- ☆16Mar 30, 2023Updated 3 years ago
- Official implementation for "Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Grad…☆10Sep 18, 2023Updated 3 years ago
- ☆11Jun 12, 2026Updated 4 months ago
- AI-Generated-Videos-Detection-Papers☆12May 22, 2026Updated 5 months ago
- ☆14Feb 11, 2025Updated last year
- ICL backdoor attack☆17Nov 4, 2024Updated last year
- XDU-计科网安方向大数据安全与隐私实验三阶梯三-数据差分隐私处理☆13Jun 25, 2022Updated 4 years 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.
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Oct 24, 2024Updated 2 years ago
- Code for "Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning", ICLR 2025.☆15Aug 30, 2026Updated 2 months ago
- This repository contains data and code used for On the Risk of Misinformation Pollution with Large Language Models (EMNLP 2023 Findings).☆17Dec 14, 2023Updated 2 years ago
- Code for the paper "Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction" …☆13Sep 6, 2023Updated 3 years ago
- ☆12Feb 22, 2024Updated 2 years ago
- ☆118Sep 30, 2026Updated last month
- Implementation of "PrivGraph: Differentially Private Graph Data Publication by Exploiting Community Information"☆17Mar 21, 2023Updated 3 years ago