🏠 Hem
Benchmarkar
📊 Alla benchmarkar 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List-applikationer 🎨 Kreativa fria sidor 🎯 FSACB - Ultimata uppvisningen 🌍 Översättningsbenchmark
Modeller
🏆 Topp 10 modeller 🆓 Gratis modeller 📋 Alla modeller ⚙️ Kilo Code
Resurser
💬 Promptbibliotek 📖 AI-ordlista 🔗 Användbara länkar

AI-ordlista

Den kompletta ordlistan över AI

162
kategorier
2 032
underkategorier
23 060
termer
📖
termer

Defensive Distillation

Defense method training a network to learn the soft probabilities of a pre-trained model, reducing sensitivity to adversarial perturbations by smoothing the decision surface.

📖
termer

Obfuscated Gradients

Phenomenon where defenses intentionally or accidentally mask gradients, creating a false impression of robustness while remaining vulnerable to alternative attacks.

📖
termer

Gradient Shattering

Technique introducing discontinuities or oscillations in the gradient landscape to disrupt iterative optimization-based attack methods.

📖
termer

Gradient Regularization

Approach penalizing high gradients during training to reduce the model's sensitivity to small input perturbations and improve overall robustness.

📖
termer

Randomized Smoothing

Method certifying robustness by adding random noise to inputs and using Gaussian smoothing techniques to guarantee certifiability bounds against adversarial attacks.

📖
termer

Input Transformation

Defense applying non-differentiable or non-invertible transformations to inputs before classification, such as compression or resampling, to neutralize adversarial perturbations.

📖
termer

Feature Squeezing

Technique reducing input feature complexity by decreasing pixel precision or color space, thereby eliminating imperceptible perturbations used in attacks.

📖
termer

Non-differentiable Defense

Protection strategy integrating non-differentiable operations into the classification pipeline to prevent attackers from efficiently computing gradients.

📖
termer

Gradient Obfuscation

Set of techniques making gradients unusable by numerical methods, including masking, crushing, or falsifying gradient information.

📖
termer

Certified Defenses

Approaches providing provable mathematical guarantees on model robustness within a specified perturbation radius, avoiding false impressions of security.

📖
termer

Jacobian-based Saliency Map Attack Defense

Countermeasures specifically designed to neutralize Jacobian-based saliency map attacks by modifying network structure or propagation mechanisms.

📖
termer

PGD-based Robustness

Evaluation and improvement of robustness using Projected Gradient Descent as a reference attack to measure and optimize model resistance.

📖
termer

Ensemble Methods

Use of multiple models with different architectures or initializations to diversify responses and reduce the effectiveness of attacks targeting a single vulnerability.

📖
termer

Lipschitz Continuity

Mathematical property guaranteeing limited variation of outputs relative to inputs, used to design networks intrinsically robust to perturbations.

📖
termer

Provably Robust Networks

Neural architectures designed with formal constraints mathematically guaranteeing their robustness under specified perturbation conditions.

📖
termer

Gradient-free Optimization Attacks

Attack methods bypassing gradient masking by using gradient-free optimization approaches such as genetic algorithms or simulated annealing.

📖
termer

Thermometer Encoding

Input encoding technique transforming continuous features into ordered binary representations, reducing the attack surface and improving robustness.

🔍

Inga resultat hittades