Here's your daily roundup of the most relevant AI and ML news for September 16, 2026. We're also covering 6 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement
arXiv:2609.07529v2 Announce Type: replace Abstract: Language-model agents are vulnerable to indirect prompt injection (IPI) during tool use: adversarial instructions hidden in untrusted tool outputs can covertly redirect legitimate task execution. Existing work often trains and evaluates defense...
Source: arXiv - Machine Learning | 10 hours ago
2. A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion
arXiv:2609.13511v1 Announce Type: cross Abstract: Large language models are increasingly benchmarked against classical machine learning for network intrusion detection (NIDS), almost always using same-dataset evaluation, and that protocol turns out to be incomplete. Evaluating XGBoost and RoBERT...
Source: arXiv - AI | 10 hours ago
3. ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect prompt injection (IPI) attacks. Existing defenses mainly rely on prompt hardening, content filtering,...
Source: arXiv - AI | 10 hours ago
4. DualView: Preventing Indirect Prompt Injection in Personal AI Agents
arXiv:2607.03821v2 Announce Type: replace-cross Abstract: Personal AI agents that run on the user's local machine automate daily tasks including web search, email, and file management. Their access to computer resources, including the network, file system, and shell, exposes them to indirect pro...
Source: arXiv - AI | 10 hours ago
5. Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits
arXiv:2609.09907v2 Announce Type: replace Abstract: Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made for stochastic bandits and non-contextual adversarial bandits, meta-learning for adversarial ...
Source: arXiv - Machine Learning | 10 hours ago
6. Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction
arXiv:2606.13621v2 Announce Type: replace-cross Abstract: Formal safety analysis determines whether a system admits a safe defense; adaptive evaluation characterizes the operating quality sustained under adversarial interaction. Both answers matter because systems with the same safety verdict ca...
Source: arXiv - Machine Learning | 10 hours ago
Industry News
7. OpenAI, Anthropic, Google have been in talks on AI safety for weeks
OpenAI confirms weeks of AI safety talks with Anthropic and Google DeepMind, as Trump's team dismisses safety concerns and pushes to keep pace with China.
Source: TechCrunch - AI | 22 hours ago
Tech & Development
8. I caught an LLM-powered recruiter with a prompt injection on LinkedIn
Article URL: https://khancyr.github.io/blog/2026/03/15/how-i-caught-an-llm-powered-recruiter-with-a-prompt-injection-on-linkedin/ Comments URL: https://news.ycombinator.com/item?id=49726928 Points: 1
Comments: 0
Source: Hacker News - AI | just now
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.