Adversarial Moral Stress Testing of Large Language Models

• URL: http://arxiv.org/abs/2604.01108v1
• Date: Wed, 01 Apr 2026 16:34:20 GMT
• Title: Adversarial Moral Stress Testing of Large Language Models
• Abstract summary: This paper introduces Adversarial Moral Stress Testing (AMST), a stress-based evaluation framework for assessing ethical robustness under adversarial multi-round interactions.<n>We evaluate AMST on several state-of-the-art LLMs, including LLaMA-3-8B, GPT-4o, and DeepSeek-v3, using a large set of adversarial scenarios generated under controlled stress conditions.
• Score: 6.225703352031606
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remains challenging, particularly under sustained adversarial user interaction. Existing safety benchmarks typically rely on single-round evaluations and aggregate metrics, such as toxicity scores and refusal rates, which offer limited visibility into behavioral instability that may arise during realistic multi-turn interactions. As a result, rare but high-impact ethical failures and progressive degradation effects may remain undetected prior to deployment. This paper introduces Adversarial Moral Stress Testing (AMST), a stress-based evaluation framework for assessing ethical robustness under adversarial multi-round interactions. AMST applies structured stress transformations to prompts and evaluates model behavior through distribution-aware robustness metrics that capture variance, tail risk, and temporal behavioral drift across interaction rounds. We evaluate AMST on several state-of-the-art LLMs, including LLaMA-3-8B, GPT-4o, and DeepSeek-v3, using a large set of adversarial scenarios generated under controlled stress conditions. The results demonstrate substantial differences in robustness profiles across models and expose degradation patterns that are not observable under conventional single-round evaluation protocols. In particular, robustness has been shown to depend on distributional stability and tail behavior rather than on average performance alone. Additionally, AMST provides a scalable and model-agnostic stress-testing methodology that enables robustness-aware evaluation and monitoring of LLM-enabled software systems operating in adversarial environments.

Related papers

• Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation [14.366084759097445]
  We propose a framework for synthesizing harmful content, leveraging persona-guided large language model (LLM) agents.<n>Our approach constructs two-dimensional user personas by integrating demographic identities and topical interests with situational harmful strategies.<n>Both human and LLM-based evaluations confirm that our framework achieves a high harmful generation success rate.
  arXiv  Detail & Related papers  (2026-04-18T14:58:02Z)
• FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering [11.609466767597093]
  FaithSteer-BENCH is a stress-testing benchmark forference-time steering.<n>It evaluates steering methods at a fixed deployment-style operating point through three gate-wise criteria: controllability, utility preservation, and robustness.<n> Gate-wise benchmark results show that existing methods do not necessarily provide reliable controllability in deployment-oriented practical settings.
  arXiv  Detail & Related papers  (2026-03-18T22:28:36Z)
• Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling [0.0]
  We introduce Accelerated Prompt Stress Testing (APST), a depth-oriented evaluation framework inspired by highly accelerated stress testing in reliability engineering.<n>APST probes behavior by repeatedly sampling identical prompts under controlled operational conditions, including temperature variation and prompt perturbation.<n>We observe safety failures using Bernoulli and binomial formulations to estimate per-inference failure probabilities, enabling quantitative comparison of operational risk across models and configurations.
  arXiv  Detail & Related papers  (2026-03-10T20:23:01Z)
• ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments [43.08480724370872]
  We introduce ConflictBench, a benchmark for evaluating human-AI conflict through 150 multi-turn scenarios.<n>We show that ConflictBench integrates a text-based simulation engine with a visually grounded world model, enabling agents to perceive, plan, and act under dynamic conditions.
  arXiv  Detail & Related papers  (2026-03-09T06:59:48Z)
• Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing [0.0]
  We introduce Accelerated Prompt Stress Testing (APST), a depth-oriented evaluation framework inspired by reliability engineering.<n>APST repeatedly samples identical prompts under controlled operational conditions to surface latent failure modes.<n>We find that models with similar benchmark-aligned scores can exhibit substantially different empirical failure rates under repeated sampling.
  arXiv  Detail & Related papers  (2026-02-12T10:09:13Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents [37.75212140218036]
  We formalize the Loss-of-Control risk and identify the previously underexamined Intrinsic Value Misalignment (Intrinsic VM)<n>We then introduce IMPRESS, a scenario-driven framework for systematically assessing this risk.<n>We evaluate Intrinsic VM on 21 state-of-the-art LLM agents and find that it is a common and broadly observed safety risk across models.
  arXiv  Detail & Related papers  (2026-01-24T07:09:50Z)
• DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios [57.327907850766785]
  characterization of deception across realistic real-world scenarios remains underexplored.<n>We establish DeceptionBench, the first benchmark that systematically evaluates how deceptive tendencies manifest across different domains.<n>On the intrinsic dimension, we explore whether models exhibit self-interested egoistic tendencies or sycophantic behaviors that prioritize user appeasement.<n>We incorporate sustained multi-turn interaction loops to construct a more realistic simulation of real-world feedback dynamics.
  arXiv  Detail & Related papers  (2025-10-17T10:14:26Z)
• On Evaluating Performance of LLM Inference Serving Systems [11.712948114304925]
  We identify recurring anti-patterns across three key dimensions: Baseline Fairness, Evaluation setup, and Metric Design.<n>These anti-patterns are uniquely problematic for Large Language Model (LLM) inference due to its dual-phase nature.<n>We provide a comprehensive checklist derived from our analysis, establishing a framework for recognizing and avoiding these anti-patterns.
  arXiv  Detail & Related papers  (2025-07-11T20:58:21Z)
• Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions [49.546479320670464]
  This paper introduces specialized metrics for benchmarking the spatial robustness of segmentation models.<n>We propose region-aware multi-attack adversarial analysis, a method that enables a deeper understanding of model robustness.<n>The results reveal that models respond to these two types of threats differently.
  arXiv  Detail & Related papers  (2025-04-02T11:37:39Z)
• Towards Evaluating the Robustness of Visual State Space Models [63.14954591606638]
  Vision State Space Models (VSSMs) have demonstrated remarkable performance in visual perception tasks. However, their robustness under natural and adversarial perturbations remains a critical concern. We present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios.
  arXiv  Detail & Related papers  (2024-06-13T17:59:44Z)
• The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks [90.52808174102157]
  In safety-critical applications such as medical imaging and autonomous driving, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks. A notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. This study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks.
  arXiv  Detail & Related papers  (2024-05-14T18:05:19Z)
• Extreme Miscalibration and the Illusion of Adversarial Robustness [66.29268991629085]
  Adversarial Training is often used to increase model robustness. We show that this observed gain in robustness is an illusion of robustness (IOR) We urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations.
  arXiv  Detail & Related papers  (2024-02-27T13:49:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.