ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “Gemma”

3 stories in the last 3d

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllModel release 1AI research 1AI safety & security 1
SeverityAllcritical 0high 0medium 0low 0info 3

Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs

Attack shows unaligned orchestrators can launder capabilities from aligned frontier LLMs via benign subtask consultation, raising Gemma-4-31B CBRN rubric score from 62.3 to 83.1.

The paper introduces capability laundering, where a weaker unaligned model decomposes a harmful task into benign-looking subproblems, queries a stronger aligned model on each, and recombines answers locally, bypassing per-interaction safety evaluations. Evaluation used GPT-5.5, Claude Opus 4.8, and Grok-4.3 as consultants to four local orchestrators on CyBench, BountyBench, and CBRN tasks. On CyBench, Gemma-4-31B recovered 8/14 candidate tasks with GPT-5.5 and 7/9 with Opus, while Muse-Glimmer-30B recovered none. Across an eight-step hypothetical bioweapon attack chain, consultation raised Gemma-4-31B's mean rubric score from 62.3 to 83.1, exposing a gap in defenses that only refuse complete harmful tasks.

arXiv cs.CR · 2d agoAI safety & security

Knowledgator Releases GLiFormer: A 575M-Parameter Encoder That Hits 91.10 F1 on Nested JSON Extraction Without Generating Tokens

Knowledgator released GLiFormer, an Apache-2.0 encoder (264M/575M) handling NER, classification, relations, and nested JSON extraction, scoring 91.10 F1.

Knowledgator Engineering released GLiFormer, a schema-conditioned encoder that performs NER, classification, relation extraction, nested JSON structuring, and embeddings without generating output tokens. GLiFormer Large v1 has 575.6M parameters and scores 91.10 F1 on nested JSON extraction, close to GPT-5.6-luna's 91.96; both checkpoints are Apache 2.0 on Hugging Face. Reported median latency is 69 ms on GPU for the base model, though relation extraction (21.33 micro-F1) still trails GLiNER-Relex and larger LLMs.

MarkTechPost · 7h agoModel release

A Zeroth-Order Paradigm for LLM Preference Alignmentnew

Researchers propose ComPO, a zeroth-order comparison-based preference alignment method with convergence guarantees that mitigates likelihood displacement in LLMs.

ComPO extracts directional information from preference pairs via comparison oracles instead of optimizing a differentiable preference loss, addressing likelihood displacement in direct alignment methods. The paper establishes convergence guarantees for the offline scheme and introduces an online variant with reverse-KL control using unlabeled policy generations. Experiments on Mistral, Llama, Gemma-2, Gemma-3, and Qwen3 models show improvements over existing direct alignment methods, including length-controlled win rates.

arXiv cs.AI / cs.LG / cs.CL · 10h agoAI research