Here's your daily roundup of the most relevant AI and ML news for July 20, 2026. Today's digest includes 1 security-focused story. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. SleeperGem Uses Three Malicious RubyGems Packages to Target Developer Machines
Cybersecurity researchers have flagged a new software supply chain attack codenamed SleeperGem targeting the Ruby ecosystem after three malicious gems were published to RubyGems with the end goal of serving additional payloads.
The rogue gems are listed below -
git_credential_manager (versio...
Source: The Hacker News (Security) | 8 hours ago
Research & Papers
2. LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
arXiv:2607.15509v1 Announce Type: cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition. Each large language model independentl...
Source: arXiv - Machine Learning | 10 hours ago
3. Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
arXiv:2508.10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations. We introduce Latent Fusion Jailbreak (LFJ), which works by pairing a harmful query with a structural...
Source: arXiv - AI | 10 hours ago
4. How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
arXiv:2605.06605v3 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.g., jailbreaks or successful task completion by an agent -- often emerge ...
Source: arXiv - Machine Learning | 10 hours ago
5. Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
arXiv:2602.24009v4 Announce Type: replace-cross Abstract: Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBRE...
Source: arXiv - Machine Learning | 10 hours ago
6. AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
arXiv:2606.02240v3 Announce Type: replace-cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither ...
Source: arXiv - AI | 10 hours ago
7. Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching
arXiv:2607.15516v1 Announce Type: new Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent). The compression literature has standardized on query-aware methods that prod...
Source: arXiv - Machine Learning | 10 hours ago
8. CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data
arXiv:2607.16122v1 Announce Type: cross Abstract: Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post training data. Most evaluation pipelines identify weak examples, topics...
Source: arXiv - Machine Learning | 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.