GradientJailbreakDetector<T>

Models & Types · AiDotNet.Safety.Text

Detects gradient-based adversarial jailbreak attacks by analyzing token-level anomalies in the input text.

Inheritance: ModelBase<T, Vector<T>, Vector<T>> → SafetyModuleBase<T> → TextSafetyModuleBase<T> → GradientJailbreakDetector<T>

For Beginners

Some attackers use mathematical optimization to craft special text that tricks AI safety filters. This text often looks like random gibberish appended to a normal prompt. This module detects such gibberish suffixes by checking whether parts of the text have unusual character patterns.

How It Works

Gradient-based attacks (GCG, AutoDAN, etc.) optimize adversarial suffixes to trigger unsafe behavior. These suffixes typically exhibit statistical anomalies detectable without model gradients: unusual character distributions, high entropy token sequences, abnormal bigram frequencies, and nonsensical subword patterns. This detector identifies such adversarial artifacts.

Detection signals:

  1. Character distribution anomaly — adversarial tokens have non-English character frequencies
  2. Bigram entropy — random-looking token sequences have unusually high bigram entropy
  3. Subword coherence — GCG tokens are often nonsensical fragments
  4. Suffix length anomaly — adversarial suffixes are unusually long appended sequences

References:

  • GradSafe: Detecting unsafe inputs via safety-critical gradient analysis (2024, arxiv:2402.13494)
  • GCG: Universal and transferable adversarial attacks on aligned LMs (2023, arxiv:2307.15043)
  • SmoothLLM: Defending LLMs against jailbreaking via randomized smoothing (2024, arxiv:2310.03684)
  • Perplexity-based jailbreak detection (Jain et al., 2023)

Constructors

Constructor Summary
GradientJailbreakDetector(double anomalyThreshold, int minSuffixLength) Initializes a new gradient-based jailbreak detector.

Properties

Property Summary
string ModuleName { get; }

Methods

Method Summary
IReadOnlyList<SafetyFinding> EvaluateText(string text)