AI ethics evidence index Search
Source-linked daily record
Evidence record 3055 · automatically gathered

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning

Training-time data poisoning during fine-tuning poses a significant threat to large language models (LLMs) deployed for abstractive text summarization, where small task-specific datasets exert disproportionate influence on model behavior. In this setting, adversaries manipulate fine-tuning data to induce persistent summarization failures, such as biased or harmful summaries, while preserving standard evaluation metrics. We present a unified post-hoc defense framework for detecting and remediatin

Record details

Published: 24 June 2026
Source: arXiv cs.CR (AI security)
Category: Research
Topics: Bias & fairness · Military & security
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: Bias & fairness · Shared topic: Military & security

GIGO and the Human Processor: A Chief Humanity Officer Review

OpenAlex · 18 March 2026

Shared topic: Bias & fairness · Shared topic: Military & security

GIGO and the Human Processor: A CHO Review

OpenAlex · 18 March 2026

Shared topic: Bias & fairness · Shared topic: Military & security

ITEP1018 - AI Assurance Proof of Concept

UK Contracts Finder — AI procurement · 18 September 2025

Shared topic: Bias & fairness

Statistical and Structural Approaches to Algorithmic Fairness

arXiv · 24 June 2026

Shared topic: Bias & fairness

Scoring Is Not Enough: Addressing Gaps in Utility-fairness Trade-offs for Ranking

arXiv · 24 June 2026

Shared topic: Bias & fairness

Retrieval-Warmed Energy-Based Reasoning: A Five-Arm Ablation Methodology for Diffusion-as-Inference on Structured Reasoning Tasks

arXiv · 25 June 2026

How to cite this record

ethics.ai (24 June 2026), “Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning,” evidence record 3055, https://ethics.ai/record/3055 (originally published by arXiv cs.CR (AI security)).

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.