Picture for Ljiljana Dolamic

Ljiljana Dolamic

NMT-Obfuscator Attack: Ignore a sentence in translation with only one word

Add code
Nov 19, 2024
Viaarxiv icon

Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?

Add code
Oct 05, 2024
Viaarxiv icon

LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts

Add code
Sep 05, 2024
Figure 1 for LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts
Figure 2 for LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts
Figure 3 for LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts
Figure 4 for LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts
Viaarxiv icon

Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysis

Add code
Jul 25, 2024
Viaarxiv icon

Do Large Language Models Exhibit Cognitive Dissonance? Studying the Difference Between Revealed Beliefs and Stated Answers

Add code
Jun 21, 2024
Viaarxiv icon

A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation

Add code
Aug 29, 2023
Viaarxiv icon

A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models

Add code
Jun 14, 2023
Viaarxiv icon

Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT

Add code
Jun 05, 2023
Viaarxiv icon

Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search

Add code
Apr 20, 2023
Viaarxiv icon

Fundamentals of Generative Large Language Models and Perspectives in Cyber-Defense

Add code
Mar 21, 2023
Viaarxiv icon