Here's your daily roundup of the most relevant AI and ML news for April 20, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement
arXiv:2604.15370v1 Announce Type: cross Abstract: Graph adversarial attacks are usually produced from the two perspectives of topology/structure and node feature, both of them represent the paramount characteristics learned by today's deep learning models. Although some defense countermeasures a...
Source: arXiv - Machine Learning | 10 hours ago
2. Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
arXiv:2604.15725v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling their deployment in high-stakes domains such as healthcare and education. While prior jailbreak attack...
Source: arXiv - Machine Learning | 10 hours ago
3. InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control
arXiv:2604.15373v1 Announce Type: cross Abstract: We propose InfoChess, a symmetric adversarial game that elevates competitive information acquisition to the primary objective. There is no piece capture, removing material incentives that would otherwise confound the role of information. Instead,...
Source: arXiv - Machine Learning | 10 hours ago
4. Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
arXiv:2603.11331v2 Announce Type: replace Abstract: Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that strong adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed w...
Source: arXiv - Machine Learning | 10 hours ago
5. LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliance
arXiv:2604.15589v1 Announce Type: cross Abstract: Existing research on large language models (LLMs) for automated code compliance has primarily focused on performance, treating the models as black boxes and overlooking how training decisions affect their interpretive behavior. This paper address...
Source: arXiv - Machine Learning | 10 hours ago
6. Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation
arXiv:2604.15388v1 Announce Type: cross Abstract: Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, training data and testbenches for these models are often scarce. This paper presents a workflow th...
Source: arXiv - AI | 10 hours ago
7. Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
arXiv:2604.15482v1 Announce Type: new Abstract: Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable knowledge, pre...
Source: arXiv - Machine Learning | 10 hours ago
8. Aletheia: Gradient-Guided Layer Selection for Efficient LoRA Fine-Tuning Across Architectures
arXiv:2604.15351v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the dominant parameter-efficient fine-tuning method for large language models, yet standard practice applies LoRA adapters uniformly to all transformer layers regardless of their relevance to the downstream tas...
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.