‹› Adaptive Attacks Expose SLM Vulnerabilities and Qualitative Insights Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Transfer Attacks Reveal SLM Vulnerabilities and Effective Noise Defenses Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Cross-Prompt Attacks and Data Ablations Impact SLM Robustness Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
Safety Alignment and Jailbreak Attacks Challenge Modern LLMs Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Audio Encoder Pre-training and Evaluation Enhance SLM Safety Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
Integrated Speech Language Models Face Critical Safety Vulnerabilities Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› SpeechVerse Unites Audio Encoder and LLM for Superior Spoken QA Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Unified Speech and Language Models Can Be Vulnerable to Adversarial Attacks Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, robustness-countermeasures, speech-language-models, spoken-question-answering, white-box-attacks
‹› SLMs Outperform Competitors Yet Suffer Rapid Adversarial Jailbreaks Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Adversarial Settings and Random Noise Reveal Speech LLM Vulnerabilities Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Datasets and Evaluation Define the Robustness of Speech Language Models Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Adversarial Attacks Challenge the Integrity of Speech Language Models Post date February 6, 2025 Post author By Phonology Technology Post categories In adversarial-attacks, black-box-attacks, jailbreaking, large-language-models, multimodal-models, robustness-countermeasures, speech-language-models, white-box-attacks
‹› Increased LLM Vulnerabilities from Fine-tuning and Quantization: Appendix Post date October 17, 2024 Post author By Quantization Post categories In adversarial-attacks, alignment-training, fine-tuning, guardrails, jailbreaking, large-language-models-(llms), quantization, vulnerabilities
Increased LLM Vulnerabilities from Fine-tuning and Quantization: Conclusion and References Post date October 17, 2024 Post author By Quantization Post categories In adversarial-attacks, alignment-training, fine-tuning, guardrails, jailbreaking, large-language-models-(llms), quantization, vulnerabilities
‹› Increased LLM Vulnerabilities from Fine-tuning and Quantization: Experiment Set-up & Results Post date October 17, 2024 Post author By Quantization Post categories In adversarial-attacks, alignment-training, fine-tuning, guardrails, jailbreaking, large-language-models-(llms), quantization, vulnerabilities
Sciencx
Sciencx