🏠 Home
Benchmark
📊 Tutti i benchmark 🦖 Dinosauro v1 🦖 Dinosauro v2 ✅ App To-Do List 🎨 Pagine libere creative 🎯 FSACB - Ultimate Showcase 🌍 Benchmark traduzione
Modelli
🏆 Top 10 modelli 🆓 Modelli gratuiti 📋 Tutti i modelli ⚙️ Kilo Code
Risorse
💬 Libreria di prompt 📖 Glossario IA 🔗 Link utili

Glossario IA

Il dizionario completo dell'Intelligenza Artificiale

162
categorie
2.032
sottocategorie
23.060
termini
📖
termini

Textual Adversarial Attack

Technique consisting of subtly modifying an input text to mislead an NLP model while preserving semantics for a human reader.

📖
termini

Character-Level Perturbation

Modification of individual characters in text (insertion, deletion, substitution) to create adversarial examples that are difficult to detect.

📖
termini

Lexical Substitution Attack

Replacement of words with semantically close synonyms that change the NLP model's prediction in a targeted manner.

📖
termini

Universal Adversarial Triggers

Specific sequences of words or characters that, when inserted into any text, systematically cause a classification error by the model.

📖
termini

Black-Box Attack

Attack conducted without knowledge of the model's internal parameters, using only the model's predictions to construct adversarial examples.

📖
termini

White-Box Attack

Attack exploiting complete knowledge of the model's architecture and gradients to generate optimal perturbations.

📖
termini

Transfer Attack

Generation of adversarial examples on a source model that retain their effectiveness on unknown target models.

📖
termini

Semantic Preservation

Constraint ensuring that textual perturbations do not alter the overall meaning of the text for a human reader.

📖
termini

Data Poisoning Attack

Malicious insertion of corrupted examples into the training set to degrade model performance during its learning phase.

📖
termini

Syntactic Perturbation

Modification of the grammatical or syntactic structure of a sentence while preserving its semantic meaning to deceive NLP models.

📖
termini

Gradient Masking

Defense technique that modifies the model's gradient to prevent optimization-based attacks, without necessarily improving actual robustness.

📖
termini

Query Attack

Black-box attack that optimizes perturbations by iteratively querying the model and analyzing its responses.

📖
termini

Semantic Robustness

Ability of an NLP model to maintain consistent predictions in the face of textual variations preserving meaning but altering form.

📖
termini

Adversarial Search Space

Set of all possible text modifications that can be applied to generate valid adversarial examples.

📖
termini

Perturbation Score

Quantitative metric evaluating the magnitude of modification applied to the original text to create an adversarial example.

📖
termini

Multi-objective Attack

Adversarial attack seeking simultaneously to deceive the model while optimizing multiple constraints such as readability or semantic preservation.

📖
termini

Adversarial Attack Detection

Defensive mechanism identifying potentially adversarial inputs based on statistical or behavioral anomalies in predictions.

🔍

Nessun risultato trovato