AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Exploring Security Vulnerabilities in Multilingual Speech Translation Systems via Deceptive Inputs

Chang Liu, Haolin Wu, Xi Yang, Kui Zhang, Cong Wu, Weiming Zhang, Nenghai Yu, Tianwei Zhang, Qing Guo, Jie Zhang

TPAMI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add more seen attack languages (EN to EN+ZH+DE+FR) (ablation)perturbation attack on Seamless Large · Spanish unseen, eps=0.1ASR: 22/60 -> 55/60Improved
add more seen attack languages (EN to EN+ZH+DE+FR) (ablation)adversarial music on Seamless Large · Spanish unseenASR: 4/10 -> 10/10Improved
add more seen attack languages (EN to EN+FR+DE) (ablation)perturbation attack on Canary · Spanish unseen, eps=0.5ASR: 1/10 -> 6/10Improved
add Target Cycle Optimization (ablation)perturbation attack · Seamless Large, eps 0.5/0.1/0.01ESIM, NSCOREImproved
add Target Cycle Optimization (ablation)adversarial music · Seamless LargeESIM, NSCOREImproved
reduce perturbation bound eps from 0.5 to 0.01perturbation attack · Seamless Large EnglishASR: 59/60 -> 32/60Hurt
add bandpass-filtered adversarial perturbation instead of random noise (ablation)perturbation attack · eps=0.1 EN attackVSIM-E: 0.4172 vs 0.1452Improved
apply 8-bit quantization to adversarial audioperturbation attack · Seamless Large eps=0.1ASR: 52/60 -> 12/60Hurt
apply noise addition (SNR 64 dB) to adversarial audioperturbation attack · Seamless Large eps=0.1ASR: 52/60 -> 45/60Hurt
apply 12 kHz resampling to adversarial audioadversarial music · Seamless LargeASR: 9/10 -> 4/10Hurt
apply 6 kHz low-pass filter to adversarial audioadversarial music · Seamless LargeASR: 9/10 -> 8/10Hurt
change music style prompt from Techno to Classical or Orchestral (ablation)adversarial music · English target, Seamless LargeASR: 9/10 -> 10/10Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy