Gradient and greedy search over token suffixes produces universal, transferable adversarial prompts that elicit objectionable outputs from aligned models including black-box commercial systems.
hub Canonical reference
Promptbench: Towards evaluating the robustness of large language models on adversarial prompts
Canonical reference. 71% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 6
baseline 1
citation-polarity summary
representative citing papers
BiAxisAudit measures LLM bias on two axes—across-prompt sensitivity via factorial grids and within-response divergence via split coding—revealing that task format explains as much variance as model choice and that 63.6% of bias signals appear in only one layer.
Structurally rich task descriptions make LLMs robust to prompt under-specification, and under-specification can enhance code correctness by disrupting misleading lexical or structural cues.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
Paraphrase sensitivity in Lean 4 autoformalization is dominated by code-generation failures that differ between undergraduate and Olympiad datasets across multiple models.
PEEM is a multi-criteria LLM-based evaluator for prompts and responses that aligns with standard accuracy while enabling zero-shot prompt optimization via feedback.
LLMs show heterogeneous robustness to five types of chain-of-thought perturbations, with MathError causing 50-60% accuracy loss in small models but scaling benefits, UnitConversion remaining hard across sizes, and ExtraSteps causing minimal degradation.
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.
LLMs show systematic output-mode collapse on closed-form prompts, with only ~22% of semantically equivalent variants preserving the requested bare-label format across five models and four tasks.
LLMs display accuracy gaps of up to 14 percentage points on the same geometry problems solely due to representation choice, with vector forms consistently weakest and a convert-then-solve prompt helping only high-capacity models.
Systematic testing of ten LLM agents across 20 tool scenarios and 14 attacks finds universal vulnerability to prompt injection enabling data exfiltration, with tooling amplifying leakage.
Baseline defenses including perplexity-based detection, input preprocessing, and adversarial training offer partial robustness to text adversarial attacks on LLMs, with challenges arising from weak discrete optimizers.
A framework with U-statistics and kernel-based metrics quantifies AI agent consistency and robustness, showing trajectory metrics outperform pass@1 rates in diagnosing failures.
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
A literature survey that taxonomizes hallucination phenomena in LLMs, reviews evaluation benchmarks, and analyzes approaches for their detection, explanation, and mitigation.
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
citing papers explorer
-
Universal and Transferable Adversarial Attacks on Aligned Language Models
Gradient and greedy search over token suffixes produces universal, transferable adversarial prompts that elicit objectionable outputs from aligned models including black-box commercial systems.
-
BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence
BiAxisAudit measures LLM bias on two axes—across-prompt sensitivity via factorial grids and within-response divergence via split coding—revealing that task format explains as much variance as model choice and that 63.6% of bias signals appear in only one layer.
-
When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
Structurally rich task descriptions make LLMs robust to prompt under-specification, and under-specification can enhance code correctness by disrupting misleading lexical or structural cues.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization
Paraphrase sensitivity in Lean 4 autoformalization is dominated by code-generation failures that differ between undergraduate and Olympiad datasets across multiple models.
-
PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses
PEEM is a multi-criteria LLM-based evaluator for prompts and responses that aligns with standard accuracy while enabling zero-shot prompt optimization via feedback.
-
Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
LLMs show heterogeneous robustness to five types of chain-of-thought perturbations, with MathError causing 50-60% accuracy loss in small models but scaling benefits, UnitConversion remaining hard across sizes, and ExtraSteps causing minimal degradation.
-
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
-
EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.
-
Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
LLMs show systematic output-mode collapse on closed-form prompts, with only ~22% of semantically equivalent variants preserving the requested bare-label format across five models and four tasks.
-
Measuring Representation Robustness in Large Language Models for Geometry
LLMs display accuracy gaps of up to 14 percentage points on the same geometry problems solely due to representation choice, with vector forms consistently weakest and a convert-then-solve prompt helping only high-capacity models.
-
Whispers in the Machine: Confidentiality in Agentic Systems
Systematic testing of ten LLM agents across 20 tool scenarios and 14 attacks finds universal vulnerability to prompt injection enabling data exfiltration, with tooling amplifying leakage.
-
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Baseline defenses including perplexity-based detection, input preprocessing, and adversarial training offer partial robustness to text adversarial attacks on LLMs, with challenges arising from weak discrete optimizers.
-
Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
A framework with U-statistics and kernel-based metrics quantifies AI agent consistency and robustness, showing trajectory metrics outperform pass@1 rates in diagnosing failures.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
-
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
A literature survey that taxonomizes hallucination phenomena in LLMs, reviews evaluation benchmarks, and analyzes approaches for their detection, explanation, and mitigation.
-
Benchmark Data Contamination of Large Language Models: A Survey
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.