Code for "Adversarial Illusions in Multi-Modal Embeddings"
☆32Aug 4, 2024Updated last year
Alternatives and similar repositories for adversarial_illusions
Users that are interested in adversarial_illusions are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆101Oct 15, 2023Updated 2 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆31Oct 10, 2022Updated 3 years ago
- Benchmarking prompt injection detections for web agents.☆20Jul 10, 2026Updated 2 weeks ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated 9 months ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆20Apr 27, 2023Updated 3 years ago
- 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.
- [NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling☆19Jan 18, 2025Updated last year
- Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)☆15Oct 8, 2020Updated 5 years ago
- template for https://cnli.me☆10Feb 27, 2025Updated last year
- ☆26Nov 21, 2020Updated 5 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Feb 27, 2020Updated 6 years ago
- verifying machine unlearning by backdooring☆20Mar 25, 2023Updated 3 years ago
- CaPC is a method that enables collaborating parties to improve their own local heterogeneous machine learning models in a setting where b…☆24Mar 16, 2022Updated 4 years ago
- ☆10Mar 17, 2021Updated 5 years ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆35Jun 29, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Code Implementation for Traceback of Data Poisoning Attacks in Neural Networks☆22Aug 15, 2022Updated 3 years ago
- ☆32Mar 16, 2025Updated last year
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years ago
- ☆33Jul 11, 2024Updated 2 years ago
- ☆10May 8, 2024Updated 2 years ago
- [ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening☆10Dec 18, 2025Updated 7 months ago
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆41Sep 17, 2025Updated 10 months ago
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic Sys…☆119Updated this week
- ☆202Apr 7, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆14Apr 6, 2025Updated last year
- SpecAuditor: Generating Audit Specifications for LLM-Driven Bug Detection (S&P 2026)☆23Jun 8, 2026Updated last month
- The source codes of TDv2 in paper: TDv2: A Novel Tree-Structured Decoder for Offline Mathematical Expression Recognition.☆12Jul 28, 2022Updated 3 years ago
- A TensorFlow implementation of light convolutional neural network (LCNN)☆12Dec 27, 2018Updated 7 years ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆51Dec 23, 2024Updated last year
- Code and full version of the paper "Hijacking Attacks against Neural Network by Analyzing Training Data"☆14Feb 28, 2024Updated 2 years ago
- safety analysis for hard-to-specify failures☆34Apr 19, 2026Updated 3 months ago
- Official Code for FedRule: Federated Rule Recommendation System with Graph Neural Networks☆14Sep 12, 2023Updated 2 years ago
- [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the…☆100Feb 3, 2026Updated 5 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.
- Datasets used for NeuralProphet tutorials☆22Jul 7, 2023Updated 3 years ago
- Large Language Models Can Be Contextual Privacy Protection Learners☆16Oct 28, 2024Updated last year
- ☆29Aug 31, 2025Updated 10 months ago
- 中外文学Part03☆10Nov 29, 2021Updated 4 years ago
- Code for CCS '23 paper "Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation"☆16Nov 17, 2023Updated 2 years ago
- My implement of InstantBooth☆14Sep 11, 2023Updated 2 years ago
- Official repository of the paper Face Presentation Attack Detection by Eacavating Causal Clues and Adapting Embedding Statistics☆14Aug 29, 2023Updated 2 years ago