ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently emerged as a promising attack paradigm. They bypass explicit safety mechanisms by replacing harmful terms in original harmful questions with benign alternatives and leveraging contextual information to induce the target model to reinterpret these alternatives as their corresponding harmful concepts. However, existing sem
Record details
Published: 4 August 2026
Source: arXiv red teaming query
Category: Research
Topics: Safety & alignment · Finance, VC & PE
Retrieved: 5 August 2026
Related evidence
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.
A Data-Centric Perspective on Tree Visualizations
arXiv cs.HC · 2 August 2026
No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks
arXiv red teaming query · 2 August 2026
People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe
arXiv · 7 August 2026
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
arXiv · 7 August 2026
Symbolic Attack Chain Generation from Atomic Red Team Techniques: An Empirical Study of Predicate Representation Granularity
arXiv red teaming query · 31 July 2026
The Easy Trap: Why LLMs Underestimate Misconception-Driven Difficulty
arXiv cs.CY · 30 July 2026
How to cite this record
ethics.ai (4 August 2026), “ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization,” evidence record 16568, https://ethics.ai/record/16568 (originally published by arXiv red teaming query).
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.