STEALTH: Steganographic Text Encoding Agnostic to Low-Level Tensor Hardware
cs.CR, cs.AI, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Perfectly Secure Steganography Using Minimum Entropy Coupling
- Non-Determinism of "Deterministic" LLM Settings
- Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
- Undetectable Watermarks for Language Models
- Robust Distortion-free Watermarks for Language Models
- QLoRA: Efficient Finetuning of Quantized LLMs
- Feedback Coding Enables Inference-Time Covert Agentic Communication
- Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- Qwen2.5 Technical Report
- Accelerating Large Language Model Decoding with Speculative Sampling
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data