arXiv Machine Learning June 4, 2026 By Avidan Shah, Jay Chooi, Jinghua Ou, Shi Feng

Covert Influence Between Language Models

Read the original on arXiv Machine Learning →

arXiv:2606. 04071v1 Announce Type: cross Abstract: As language models increasingly consume one another's outputs, covert influence -- a phenomenon where a sender's payload (the behavioral disposition it is conditioned to propagate) transfers to a receiver through carriers undetectable by humans -- becomes a growing risk.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 2

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

arXiv:2606. 00566v1 Announce Type: new Abstract: As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type.

By Mohammed Sameer Syed (University of Arizona), Rozhin Yasaei (University of Arizona)

llms 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 Machine Learning

Jun 5

Steering Vectors are an Adversarial Attack Surface

arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.

By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a

llms fine-tuning multimodal safety

arXiv Machine Learning

Jun 2

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

arXiv:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.

By Yiwei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu, Sijia Liu

llms safety

arXiv AI

Jul 28

How Context Attribution Handles What the Model Already Knows

arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.

By Quoc-Huy Trinh, Lin Zhu, Sebastian Szyller

llms benchmarks

arXiv AI

Aug 5

Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models

arXiv:2510. 22014v2 Announce Type: replace-cross Abstract: Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed content.

By Sarah Ball, Niki Hasrati, Alexander Robey, Avi Schwarzschild, Frauke Kreuter, Zico Kolter, Andrej Risteski

llms safety

Related stories

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

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

Steering Vectors are an Adversarial Attack Surface

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

How Context Attribution Handles What the Model Already Knows

Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models