AI誤「拆面」ICE特工 社交網絡掀混亂

Ai




AI生成嘅明尼阿波利斯移民執法局特工相片引發混亂

喺明尼阿波利斯發生致命槍擊案後,涉事嘅移民執法局(ICE)特工相片開始喺網上流傳。雖然呢位特工喺現場目擊者拍嘅影片中戴住口罩,但喺好多社交媒體帖文上,佢卻係冇戴口罩嘅模樣。呢張「無口罩」嘅相片似乎係由xAI嘅生成式人工智能聊天機械人Grok製造,係應用戶要求「拆口罩」而生成嘅。

NPR同時公布咗戴口罩同無口罩兩張圖片,展示AI點樣被用嚟操控新聞事件嘅真實證據。不過專家警告,利用AI「拆口罩」根本唔可信,因為AI無辦法準確還原真實面貌。

加州大學柏克萊分校專門研究數碼影像分析嘅哈尼·法里德教授喺電郵中向NPR表示:「AI強化影像往往會產生幻覺式嘅面部細節,令圖像雖然清晰,但喺生物識別方面可能完全唔準確。」

儘管如此,呢張AI生成嘅無口罩相片喺星期三晚間開始流傳,仲配咗一個名叫Steve Grove嘅名字,來源未明。到星期四早上,呢個名字引發咗對兩個無關事嘅Steve Grove嘅網上憤怒攻擊。

明尼蘇達州《星報》就發表聲明,指佢哋正監察一場有組織嘅網絡錯誤資訊行動,錯誤地指出涉案特工身份。聲明強調,該特工同《星報》冇任何關聯,呼籲公眾睇信由訓練有素嘅記者報導嘅真實資訊,而唔係機械人產生嘅內容。

其中一位被誤認嘅Steve Grove係密蘇里州斯普林菲爾德嘅槍械店老闆。佢話:「我唔會用『Steve』呢個名,我唔喺明尼蘇達,我唔係ICE員工,我頭髮仲有20吋長,但啲人就係咁亂講。」

另一位Steve Grove係《明尼蘇達星報》嘅發行人。報社表示會繼續追蹤呢個錯誤資訊嘅網絡行動。

同時,NPR同其他媒體已經確認,涉事ICE特工係Jonathan Ross。法院文件顯示,Ross喺去年六月於明尼阿波利斯附近嘅布盧明頓市一次交通攔查中,曾被一輛車拖行。

編輯評論:
呢宗事件凸顯咗AI生成內容喺現代媒體環境帶嚟嘅嚴重挑戰。雖然AI技術可以幫助提升影像清晰度或者創造藝術作品,但當佢被用嚟「修補」或「還原」真實人物面貌時,往往會產生誤導甚至錯誤資訊。尤其喺公共安全同司法事件中,AI生成嘅假象可能引發誤認,損害無辜人士名譽,甚至影響公眾對真相嘅判斷。

香港同全球嘅媒體同用戶都應該提高對AI生成內容嘅警覺,學識辨識真偽,唔好盲目相信機械人「還原」嘅圖像。記者同媒體有責任公開透明地揭示AI技術嘅限制,避免成為錯誤資訊嘅幫凶。

同時,網絡平台亦應加強監管,阻止錯誤資訊擴散,並為被誤指控嘅無辜人士提供有效救濟渠道。呢件事提醒我哋,科技發展快,但倫理同監管嘅步伐唔可以落後,否則真相同公義都會被扭曲。

以上文章由GPT 所翻譯及撰寫。而圖片則由GEMINI根據內容自動生成。

🎨 Nano Banana Pro 圖像生成器|打幾句說話就出圖

想畫人像、產品圖、插畫?SSFuture 圖像生成器支援 Flux Gemini Nano Banana Pro 改圖 / 合成, 打廣東話都得,仲可以沿用上一張圖繼續微調。

🆓 Flux 模型即玩,不用登入
🤖 登入後解鎖 Gemini 改圖
📷 支援上載參考圖再生成
⚡ 每天免費額度任你玩
✨ 即刻玩 AI 畫圖
A rugged post-apocalyptic survivor standing in a wasteland, hyper-realistic portrait. A young man with a shaved military-style haircut, dirt- and blood-stained face, visible scars, intense determined eyes. Wearing layered tactical clothing: torn and weathered jacket, patched sleeves, multiple scarves and cloth wraps in earthy tones, tactical pants with reinforced padding. Covered in survival gear: large worn backpack, utility pouches on chest and waist, rope, knives, handmade tools, makeshift firearm at the hip. Textures of dust, rust, scratches on all equipment. Cinematic dystopian lighting, muted earthy color palette, shallow depth of field, dramatic storytelling atmosphere, ultra-detailed, photorealistic, 50mm lens. Generate an ultra-realistic, highly ultra-detailed, 8k resolution with 1080x1080 pixel, true-to-life portrait of me using the uploaded image for reference (preserved the likeness and the original face for reference). Create a portrait of a  fair-skinned woman with long, curly dark hair styled in a high ponytail, her head turned to the side, her expression neutral and serene; her makeup features defined eyebrows, subtle eyeliner, light blush, and glossy lips; she wears dangling earrings with a floral design; she has a piercing in her ear; the image is in ultra-high 8K resolution, showcasing detailed skin textures, crisp edges, and sharp focus on her eyes; a medium shot, taken from the side to emphasize her profile, with a shallow depth of field that softly blurs the background; soft, diffused lighting illuminates her face evenly, creating subtle shadows and highlights, with a warm color palette of soft browns and creams; she is wearing a dark strapless top; the background is a soft, neutral tone, ensuring the focus remains on the subject; no additional props are present; photorealistic style, akin to a raw camera capture, is achieved using an 85mm lens, ISO 100, and an aperture of f/2.0 for a shallow depth of field and soft background blur.

➖Additional details:
- Negative Prompt: whimsical , doll skin, plastic skin, cartoon, 3d render, cgi,a low poly, painting, drawing, sketch, anime, deformed, bad anatomy, mutated hands, extra limbs, low quality, blurry, artifacts, plastic skin, out of frame, out of focus, wrong spelling, rumble letters, missing letter, blurry letter, blurry face, lowres, pixelated, jpeg artifacts, repeated face and repeated word. add lotso and hamm

🔥 CHATGPT PLUS 帳戶出租

唔使外國信用卡、送埋 VPN,輕鬆即用!

1個月 HK$118|1年 HK$1288|獨立帳號 🎁

💳 支援 PayMe / 轉數快 / Alipay / 信用卡

✨ 我哋亦可以代升級你的帳戶!

🚀 即刻睇詳情