Newton bilevel methods drop the lower-level strong-convexity assumption
Experiments cover synthetic tasks, data hyper-cleaning, and GPT-2 reweighting, with claimed better complexity than GALET and sl-BAMM.
36
- Mentions · 7d0
- Mentions · 30d3
- All mentions13
- First seenSep 8, 2026
- Last mentioned23d ago
Timeline
13 articles · newest firstDP-μP transfers learning rates under differential privacy
Scaling rules cover DP-SGD, DP-Adam, and DP-Muon on MLP, ViT, and GPT-2.
40
LLM-Attacker standardizes privacy tests for split language models
In a GPT-2 test, returned gradients raised token recovery from 94.20% to 97.38% and exact-document recovery from 13.71% to 37.77%.
48
Inner Momentum for Differentially Private Muon
Averaging per-example Muon gradients over recent model snapshots before clipping bounds distortion and improves differentially private GPT-2 fine-tuning.
25
What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document
Split-learning observers recover 97% of GPT-2 tokens; gradients lift exact document recovery from 14% to 38%.
58
Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?
Untied embeddings beat weight tying for decoder-only LLMs under DP-SGD, raising accuracy and cutting memory by over 60%.
38
PassGPT+: Leveraging Linguistic Priors for Password Modeling
PassGPT+ adapts GPT-2 priors for passwords, recovering 22.53% of RockYou held-out passwords at 10^8 guesses.
48
Attention Function as an Intrinsic Inductive Bias: How Models' Behavior Diverges in Novel Contexts
A fixed softmax-sigmoid attention mix barely changes GPT-2 in-distribution loss but shifts out-of-distribution perplexity sharply.
36
Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?
Circuits that match GPT-2's correct answers often fail to reproduce most of its errors.
55
Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B
Researchers propose Sampled Layerwise Proofs to audit outsourced LLM inference through Llama-2-70B.
48
Transformers Explained Visually
Transformer Explainer offers an interactive GPT-2-powered visualization teaching transformer architecture; educational content with no security relevance.
3
Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Study of 450,000 GPT-lineage completions finds safety training transforms gender discrimination into subtle 'harm laundering' that toxicity classifiers miss.
42
When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay
Researchers derive an exact law linking learning-rate schedules and weight decay in normalized networks, pinpointing when scale-invariant optimization destabilizes.
30
Appears with
- Qwen3-0.6Bai model · 1
- GPT-2product · 1
- PassGPT+ai model · 1
- PassGPTai model · 1
- OpenAIvendor · 1
- TinyLlama-1.1Bai model · 1
- GPT-5ai model · 1
- OpenAIorganization · 1
- LLM-Attackerproduct · 1
- PassDiffusionai model · 1
- Llama-2-70Bai model · 1
- Muonorganization · 1
- GPT-4ai model · 1
- DistilGPT2ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.