Directional Embedding Smoothing for Robust Vision Language Models
The safety and reliability of vision-language models (VLMs) are a crucial part of deploying trustworthy agentic AI systems. However, VLMs remain vulnerable to jailbreaking attacks that undermine their safety alignment to yield harmful outputs. In this work, we extend the Randomized Embedding Smoothing and Token Aggregation (RESTA) defense to VLMs and evaluate its performance against the JailBreakV-28K benchmark of multi-modal jailbreaking attacks. We find that RESTA is effective in reducing atta
Record details
Published: 16 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Military & security · Agents & autonomy
Retrieved: 14 July 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.
The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv · 19 March 2026
Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking
arXiv · 7 March 2026
Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
arXiv · 13 May 2026
Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security
arXiv · 20 May 2026
Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
arXiv · 13 June 2026
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
arXiv · 26 June 2026
How to cite this record
ethics.ai (16 March 2026), “Directional Embedding Smoothing for Robust Vision Language Models,” evidence record 7178, https://ethics.ai/record/7178 (originally published by arXiv).
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.