A canary injection protocol for linking observed AI agent behavior to the responsible account at the hosting vendor, with robust variants for adversarial filtering.
Title resolution pending
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Unsupervised style representations learned via paraphrase inversion enable competitive few-shot and zero-shot AI-text detection with better generalization to unseen LLMs than supervised baselines.
Modified classical opinion dynamics models with a bias term capture LLM network opinion evolution better than naive averaging, reducing mean opinion error by up to 88% and generalizing across models, topics, and networks.
LLMs discover regulatory loopholes in simulated societal environments through reward hacking during RL training.
Agentic AI eliminates the fidelity-scale tradeoff in deception, enabling the Infinite Impostor attack that hijacks trusted relationships at mass scale and requiring a shift to suspect-by-default security based on evaluating actions rather than actors.
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
A sender manipulates election outcomes via targeted uninformative messages that mimic exogenous voter signals, with influence rising in signal precision and falling in polarization; costly messaging leads to selective targeting.
AutoDAN automatically generates semantically meaningful jailbreak prompts for aligned LLMs via a hierarchical genetic algorithm, achieving higher attack success, cross-model transferability, and universality than baselines while bypassing perplexity defenses.
LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
IDO uses channel-wise reweighting, Gaussian modeling of factual uncertainty, and incongruity contrastive learning to achieve SOTA multimodal fake news detection.
Empirical tracing across model families shows verification precedes and outlasts generation for facts, with updates producing simultaneous verification of old and new answers.
GUARD automates generation of guideline-violating questions and jailbreak diagnostics to test LLM compliance with government ethics guidelines, validated empirically on eight models and extended to vision-language models.
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
Proposes an IMS-based SOCMINT framework and pipeline for human-centred mitigation of AI-mediated information manipulation, building on existing VIGINUM/EEAS usage.
Introduces the ClausewitzGPT equation as a mathematical formulation to quantify risks in LLM-augmented information operations, drawing on Clausewitz principles and emphasizing ethical autonomous AI agents.
citing papers explorer
-
An Independent Safety Evaluation of Kimi K2.5
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
-
Jailbroken: How Does LLM Safety Training Fail?
LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.
-
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.