arXiv AI

Synchronized Logit Steering: Real-world Steganography

arXiv:2608. 14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text.

arXiv AI

Jun 9

Steganography Without Modification: Hidden Communication via LLM Seeds

arXiv:2606. 09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions.

By Felix M\"achtle, Jonas Sander, Sebastian Berndt, Ben Weimar, Nils Loose, Thomas Eisenbarth

llms nlp safety

arXiv AI

Jul 20

Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models

arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.

By Charles Westphal, Keivan Navaie, Fernando E. Rosas

llms rag fine-tuning safety

arXiv Machine Learning

Jun 9

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

arXiv:2606. 09411v1 Announce Type: cross Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs.

By Charles Westphal, Timothy Douglas, Keivan Navaie, Tiago Pimentel, Fernando E. Rosas

llms fine-tuning benchmarks

arXiv AI

Jun 30

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

arXiv:2606. 28425v1 Announce Type: cross Abstract: Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels.

By Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa, Christian Schroeder de Witt

llms agents safety

arXiv AI

Aug 5

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach

arXiv:2608. 02698v1 Announce Type: cross Abstract: Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrastructure.

By Mohamed Chahine Ghanem

llms agents

arXiv AI

Jun 9

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

arXiv:2606. 08403v1 Announce Type: cross Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views.

By Mudit Sinha, Sanika Chavan

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 4

Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

arXiv:2606. 04141v1 Announce Type: cross Abstract: LLM agents often place sensitive credentials in the same context window as untrusted retrieved content, creating a direct path for indirect prompt injection to induce credential exfiltration.

By Kargi Chauhan, Pratibha Revankar

llms agents benchmarks

arXiv AI

Jul 7

NEST: Nascent Encoded Steganographic Thoughts

arXiv:2602. 14095v2 Announce Type: replace Abstract: Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model agents; however, this oversight is compromised if models learn to conceal their reasoning.

By Artem Karpov

llms rag agents safety

arXiv AI

Jul 2

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

arXiv:2607. 01208v1 Announce Type: cross Abstract: Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale.

By Shayan Talaei, Abhinav Chinta, Devvrit Khatri, Amin Karbasi, Azalia Mirhoseini, Amin Saberi

llms efficiency safety

arXiv AI

Jul 8

Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

arXiv:2607. 05744v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools.

By Mohammadreza Rashidi

agents nlp

arXiv Machine Learning

Jul 1

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

arXiv:2605. 01133v3 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks.

By Lingxi Zhang, Guangtao Zheng, Hanjie Chen

llms rag agents safety

arXiv Machine Learning

Jun 4

Bypassing Prompt Guards in Production with Controlled-Release Prompting

arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.

By Jaiden Fairoze, Sanjam Garg, Keewoo Lee, Mingyuan Wang

llms safety

Related stories