🏠 Home
Benchmark Hub
📊 All Benchmarks 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List Applications 🎨 Creative Free Pages 🎯 FSACB - Ultimate Showcase 🌍 Translation Benchmark
Models
🏆 Top 10 Models 🆓 Free Models 📋 All Models ⚙️ Kilo Code
Resources
💬 Prompts Library 📖 AI Glossary 🔗 Useful Links

AI Glossary

The complete dictionary of Artificial Intelligence

162
categories
2,032
subcategories
23,060
terms
📖
terms

Black-Box Attack

Adversarial attack conducted without knowledge of the target model's internal architecture, weights, or hyperparameters. The attacker can only interact with the model's inputs and outputs.

📖
terms

Transfer Attack

Technique where an adversarial example generated against a source model is used to fool a different target model. Exploits the similarity of decision boundaries between models trained on similar data.

📖
terms

Query-Based Attack

Iterative attack method that sends multiple queries to the model to observe its responses and progressively adjust the adversarial example. Limited by the allowed query budget.

📖
terms

Model Extraction

Process aiming to replicate or approximate a proprietary model by systematically querying it. Enables the creation of a substitute model for subsequent attacks.

📖
terms

Decision Inversion Attack

Approach that attempts to reconstruct internal features or training data from the model's decisions. Exploits information leaked by the model's outputs.

📖
terms

Boundary Attack

Attack that focuses on instances close to the target model's decision boundary. Seeks to find the minimum perturbations necessary to change the classification.

📖
terms

Substitute Attack

Strategy consisting of training a local substitute model to mimic the behavior of the target model. The substitute is then used to generate adversarial examples.

📖
terms

Oracle Attack

Method using an external oracle to evaluate attack success when the target model does not provide confidence probabilities. Relies on binary or qualitative responses.

📖
terms

Gradient Approximation Attack

Technique estimating the target model's gradient using finite differences or numerical methods. Enables gradient-based attacks without direct access to gradients.

📖
terms

Differential Evolution Attack

Metaheuristic optimization algorithm using mutation and crossover operators to find adversarial examples. Particularly effective in complex search spaces.

📖
terms

Grid Search Attack

Systematic approach exploring the perturbation space according to a predefined grid. Simple but often inefficient in high dimensions due to the curse of dimensionality.

📖
terms

Bayesian Optimization Attack

Global optimization method building a probabilistic model of the objective function to guide the search for adversarial examples. Effective with a limited query budget.

📖
terms

Reinforcement Learning Attack

Framework where an agent learns to generate adversarial perturbations through interaction with the target model. Formulates the problem as a Markov decision process.

📖
terms

ZOO Attack

Zeroth Order Optimization algorithm applying zero-order optimization to find adversarial examples. Estimates gradients through random coordinate differences.

📖
terms

NES Attack

Natural Evolution Strategy applied to black-box adversarial attacks. Uses gradient estimation through sampling from Gaussian distributions for optimization.

📖
terms

Square Attack

Score-based attack using random square perturbations to evade gradient-based defenses. Particularly effective against randomized models.

📖
terms

Attaque par HopSkipJump

Algorithme d'attaque par décision binaire ne nécessitant qu'un accès à la classe prédite. Utilise une recherche par sauts progressifs vers la frontière de décision.

📖
terms

Attaque par Boundary Attack

Méthode itérative marchant le long de la frontière de décision pour trouver des exemples adversariaux avec perturbation minimale. Ne requiert qu'un accès à la prédiction finale.

🔍

No results found