Here's your daily roundup of the most relevant AI and ML news for September 29, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
arXiv:2607.28959v2 Announce Type: replace Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs). While existing mitigation strategies, e.g., la...
Source: arXiv - Machine Learning | 10 hours ago
2. CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents
arXiv:2609.34463v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly rely on external tools and content, exposing them to indirect prompt injection (IPI). This threat has motivated a wide range of defenses, among which training-based defenses are often regarded ...
Source: arXiv - AI | 10 hours ago
3. AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents
arXiv:2606.15057v3 Announce Type: replace-cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work has proposed a variety of defensive approaches against IPI which can be grouped into three broad categories: prompt-level, filt...
Source: arXiv - AI | 10 hours ago
4. AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
arXiv:2609.32602v1 Announce Type: new Abstract: Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with white-box access to one model to compromise independently deployed systems. This creates a shared vu...
Source: arXiv - Machine Learning | 10 hours ago
5. Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection
arXiv:2609.32691v1 Announce Type: cross Abstract: LLM agents that invoke privileged tools are vulnerable to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved data hijack the agent's actions. A growing body of work evaluates defenses against IPI, but the val...
Source: arXiv - Machine Learning | 10 hours ago
6. Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning
arXiv:2609.33628v1 Announce Type: new Abstract: Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injection leverage reinforcement learning (RL) to train an attacker LLM to generate effective injected p...
Source: arXiv - Machine Learning | 10 hours ago
7. One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs
arXiv:2609.33833v1 Announce Type: cross Abstract: Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and become widely deployed, assessing their vulnerability to such attacks is essential for their safe...
Source: arXiv - Machine Learning | 10 hours ago
8. Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
arXiv:2602.01750v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores while violating human intent. Existing mitigations rely on ...
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.