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
- Speech recognition with federated learning☆11Jan 9, 2020Updated 6 years ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated 9 months ago
- ☆26Dec 1, 2022Updated 3 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- 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
- template for https://cnli.me☆10Feb 27, 2025Updated last year
- ☆26Nov 21, 2020Updated 5 years ago
- [NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling☆19Jan 18, 2025Updated last year
- verifying machine unlearning by backdooring☆20Mar 25, 2023Updated 3 years ago
- ☆33Jul 11, 2024Updated last year
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆35Jun 29, 2025Updated last year
- ☆10Mar 17, 2021Updated 5 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Feb 27, 2020Updated 6 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- 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
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years ago
- ☆20Feb 11, 2024Updated 2 years ago
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆40Sep 17, 2025Updated 9 months ago
- Code and full version of the paper "Hijacking Attacks against Neural Network by Analyzing Training Data"☆14Feb 28, 2024Updated 2 years ago
- [ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening☆10Dec 18, 2025Updated 6 months ago
- ☆10May 8, 2024Updated 2 years ago
- ☆25May 28, 2025Updated last year
- ☆200Apr 7, 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.
- The source codes of TDv2 in paper: TDv2: A Novel Tree-Structured Decoder for Offline Mathematical Expression Recognition.☆12Jul 28, 2022Updated 3 years ago
- ☆14Apr 6, 2025Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆139Feb 19, 2025Updated last year
- Advanced Embodied Intelligence Brain Model☆37Nov 5, 2025Updated 8 months ago
- Code for Robust Fine-tuning (RbFT)☆19Jan 31, 2025Updated last year
- Get CLIP ViT text tokens about an image, visualize attention as a heatmap.☆15Aug 8, 2023Updated 2 years ago
- [AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks☆46Nov 24, 2025Updated 7 months ago
- Official Code for FedRule: Federated Rule Recommendation System with Graph Neural Networks☆14Sep 12, 2023Updated 2 years ago
- Datasets used for NeuralProphet tutorials☆22Jul 7, 2023Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks☆13Feb 26, 2023Updated 3 years ago
- Codes of PostEdit☆23Apr 28, 2025Updated last year
- ☆29Aug 31, 2025Updated 10 months ago
- Responsible Robotic Manipulation☆16Aug 31, 2025Updated 10 months ago
- ENACT is a benchmark that evaluates embodied cognition through world modeling from egocentric interaction. It is designed to be simple an…☆52Nov 27, 2025Updated 7 months ago
- Large Language Models Can Be Contextual Privacy Protection Learners☆16Oct 28, 2024Updated last year
- ☆23Sep 17, 2024Updated last year