Daily Radar — 2026-07-09

Window: 2026-07-09, plus high-relevance preprints not previously reported and newly-surfaced peer-reviewed work · Sources swept: OpenReview (ICLR 2026), arXiv (cs.CL/cs.LG/cs.CR/cs.AI), lab blogs Counts: 0 peer-reviewed · 1 preprints · 0 forum/blog

Top 1 (priority order)

1. RepSelect: Robust LLM Unlearning via Representation Selectivity

• Authors / venue: (Authors not publicly resolved) — arXiv preprint (Jun 2026)
• Why it ranks here: Addresses the key robustness gap in machine unlearning for LLMs — existing methods forget shallowly and are reversed by fine-tuning or few-shot prompting; RepSelect achieves 4–50× deeper forgetting across four model families.
• Technical summary: Before each unlearning update, RepSelect collapses the top principal components of the parameter gradient into the forget-set-specific representation subspace, leaving the complement (general capability directions) unaffected. This selective projection prevents the forgetting from bleeding into general-purpose representations while concentrating the gradient signal on dimensions that only the forget set populates. Evaluated across four model families spanning dense and Mixture-of-Experts architectures (Llama 3, Qwen 3.5, Gemma 4 E4B, DeepSeek V2 Lite) on biohazardous knowledge and abusive tendencies. RepSelect achieves a 4–50× reduction in post-relearning accuracy compared to the strongest baselines, and is near-perfectly robust to few-shot attacks that easily reverse gradient-descent-based unlearning methods.

Notes

Written before the repeat cleanup of 2026-09-10; may refer to entries listed under ‘Removed repeats’ below.

• Papers covered in the Jul 7 report (DIJA, PAD, Non-Linear Representation Dilemma, Breaking Bad, Step-Wise Refusal Dynamics, Fragile Guardrail, Adaptive Steering & Remasking, Mechanistic Layer-wise Vulnerabilities, Jailbreak Leaves a Trace, Vera safety testing) and the Jul 8 report (IEEE S&P Plugin Injection, ICML Oral Data Attribution, Bootstrapped Monitoring, Many Circuits One Mechanism, FARMA, ADI, Causal Abstraction Metrics, Out-of-Band Defenses Eval, BARRIER Unlearning, Unsupervised Causal Abstractions) are excluded from today’s ranking.
• No new arXiv papers with IDs 2607.06xxx or above were found in the sweep; the freshest preprint retrieved is 2607.00481 (Jul 1). The arXiv pipeline may yield higher-ID July 2026 papers in tomorrow’s sweep.
• The dLLM mech interp cluster (#4 Steering Without Breaking + prior days’ DIJA/PAD/Step-Wise Refusal/Fragile Guardrail/Adaptive Steering) is now substantial; flagged for the weekly roundup.
• #2 (Robust Harmful Features) provides a potential mechanistic target (ACH suppression) for the defenses studied in prior daily reports; flagged for weekly synthesis.
• The ICLR 2026 SAE paper (#1) is the only peer-reviewed item today; search did not surface additional newly-accepted conference papers in this cycle.

Removed repeats

9 entries removed on 2026-09-10 because the paper had already been covered by an earlier report:

• 2510.02917 — Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders (first covered 2026-07-02)
• 2606.28153 — Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models (first covered 2026-07-01)
• 2607.00481 — Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces (first covered 2026-07-04)
• 2605.10971 — Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models (first covered 2026-07-01)
• 2606.04027 — MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models (first covered 2026-07-02)
• 2606.22673 — AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent (first covered 2026-07-02)
• 2606.06333 — Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability (first covered 2026-07-02)
• 2606.10525 — Assessing Automated Prompt Injection Attacks in Agentic Environments (first covered 2026-07-03)
• 2606.26620 — Discovering Millions of Interpretable Features with Sparse Autoencoders (first covered 2026-07-02)