Mining a directly-follows workflow graph from black-box conversations with an LLM agent enables structurally targeted boundary testing that covers 23–38 distinct stateful boundaries per agent, roughly doubling prompt-only baselines.
Ignore previous prompt: Attack techniques for language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
citing papers explorer
-
Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
Mining a directly-follows workflow graph from black-box conversations with an LLM agent enables structurally targeted boundary testing that covers 23–38 distinct stateful boundaries per agent, roughly doubling prompt-only baselines.
-
LLM-Agnostic Semantic Representation Attack
SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.