PulseAugur
EN
LIVE 20:17:41

New gaslighting attacks reveal 24% accuracy drop in speech LLMs

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a new method to test the vulnerability of speech-based large language models (LLMs) to manipulative prompts, termed "gaslighting attacks." These attacks employ five strategies—Anger, Cognitive Disruption, Sarcasm, Implicit, and Professional Negation—to evaluate how LLMs respond to misleading or overriding input. Across five different speech and multi-modal LLMs, these attacks led to an average accuracy decrease of 24.3%, highlighting significant behavioral vulnerabilities in current speech AI systems and underscoring the need for more robust and trustworthy technology. AI

IMPACT Introduces novel attack vectors that could compromise speech AI systems, necessitating new safety and robustness research.

RANK_REASON Academic paper introducing a new attack methodology and benchmark for speech LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New gaslighting attacks reveal 24% accuracy drop in speech LLMs

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper introducing a new attack methodology and benchmark for speech LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
124 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Jinyang Wu, Bin Zhu, Xiandong Zou, Qiquan Zhang, Xu Fang, Pan Zhou ·

    Benchmarking Gaslighting Attacks Against Speech Large Language Models

    arXiv:2509.19858v2 Announce Type: replace Abstract: As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied ad…

RELATED TOPICS