Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 8 of 8 for “"Model Watermarking"”.

  1. Machine Learning Model Watermarking through DRAM PUFs

    … rising cost of training, security concerns over model theft have also emerged, where an adversarial party may replicate a pre-trained model without proper authorization and deploy it for their advantage. Watermarking serves as a tool that, in such scenarios, allows the legitimate owner to claim …

    vt Repository record for Machine Learning Model Watermarking through DRAM PUFs (opens in a new tab)

  2. Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking

    … the computational effort invested in training ML models, thereby certifying the authenticity and reproducibility of the training process. Yet PoL, when deployed in isolation, remains vulnerable to sophisticated spoofing attacks that manipulate its subset-verification pathways and tolerance …

    embry-riddle Repository record for Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking (opens in a new tab)

  3. Reliability of Machine Learning Models in the Real World

    … paper, we’ll first explore methods to verify a model’s reliability in diverse scenarios, including classification, detection, auctions, and watermarking. We’ll then discuss the challenges and limitations of these verification techniques in real-world situations and suggest potential remedies. …

    maryland Repository record for Reliability of Machine Learning Models in the Real World (opens in a new tab)

  4. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    In recent years, large language models have made extensive strides that have made distinguishing human-generated text from machine-generated text increasingly more difficult. Recent works have targeted the issue of detecting machine-generated text by following one of two methodologies: (i) …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  5. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    In recent years, large language models have made extensive strides that have made distinguishing human-generated text from machine-generated text increasingly more difficult. Recent works have targeted the issue of detecting machine-generated text by following one of two methodologies: (i) …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  6. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    In recent years, large language models have made extensive strides that have made distinguishing human-generated text from machine-generated text increasingly more difficult. Recent works have targeted the issue of detecting machine-generated text by following one of two methodologies: (i) …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  7. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    In recent years, large language models have made extensive strides that have made distinguishing human-generated text from machine-generated text increasingly more difficult. Recent works have targeted the issue of detecting machine-generated text by following one of two methodologies: (i) …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  8. Poisoning Attacks in Deep Learning Security

    … poisoning, which compromises training data, and model poisoning, which manipulates the training process, are among the most pressing threats, aiming either to degrade performance or insert hidden backdoors. Backdoored models behave normally under typical conditions but produce attacker-specified …

    wurz-thes Repository record for Poisoning Attacks in Deep Learning Security (opens in a new tab)