AI ethics evidence index Search
Source-linked daily record
Evidence record 6479 · automatically gathered

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious queries, which either introduce substantial latency or suffer from randomness in text generation. To overcome these limitations, we propose SelfGrader, a lightweight guardrail method that formulates jailbreak detection as a numerical grading problem using anchored

Record details

Published: 1 April 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Safety & alignment

Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once

arXiv · 2 April 2026

Shared topic: Safety & alignment

NED-Tree: Bridging the Semantic Gap with Nonlinear Element Decomposition Tree for LLM Nonlinear Optimization Modeling

arXiv · 2 April 2026

Shared topic: Safety & alignment

CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders

arXiv · 2 April 2026

Shared topic: Safety & alignment

Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction

arXiv · 1 April 2026

Shared topic: Safety & alignment

Aligning Recommendations with User Popularity Preferences

arXiv · 1 April 2026

Shared topic: Safety & alignment

Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving

arXiv · 2 April 2026

How to cite this record

ethics.ai (1 April 2026), “SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits,” evidence record 6479, https://ethics.ai/record/6479 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.