Here's your daily roundup of the most relevant AI and ML news for May 21, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
arXiv:2605.19147v1 Announce Type: cross Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA pat...
Source: arXiv - AI | 10 hours ago
2. Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
arXiv:2605.19966v1 Announce Type: cross Abstract: Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point detection ...
Source: arXiv - AI | 10 hours ago
3. Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
arXiv:2410.15362v2 Announce Type: replace-cross Abstract: Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks that attempt to bypass guardrails via adversarial prompts. Among existing approaches, the Greedy ...
Source: arXiv - AI | 10 hours ago
4. FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
arXiv:2603.01712v2 Announce Type: replace-cross Abstract: Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning a...
Source: arXiv - Machine Learning | 10 hours ago
5. Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
arXiv:2602.04998v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent studies have proposed alternative initialization strategies, architectural modifications, and op...
Source: arXiv - AI | 10 hours ago
6. An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
arXiv:2605.20521v1 Announce Type: new Abstract: Fine-tuning adapts a pretrained machine learning model to a small, sensitive dataset, but this process risks memorizing individual new data points, making the model vulnerable to adversaries who seek to extract sensitive information. In this work, ...
Source: arXiv - Machine Learning | 10 hours ago
7. Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
arXiv:2605.19485v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional safety risks;...
Source: arXiv - AI | 10 hours ago
8. DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
arXiv:2605.18868v1 Announce Type: cross Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined...
Source: arXiv - AI | 10 hours ago
About This Digest
This digest is automatically curated from leading AI and tech news sources, filtered for relevance to AI security and the ML ecosystem. Stories are scored and ranked based on their relevance to model security, supply chain safety, and the broader AI landscape.
Want to see how your favorite models score on security? Check our model dashboard for trust scores on the top 500 HuggingFace models.